GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration
Search

Find a vulnerability

Search criteria Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.

    316 vulnerabilities by MervinPraison

    CVE-2026-57148 (GCVE-0-2026-57148)

    Vulnerability from nvd – Published: 2026-09-15 10:32 – Updated: 2026-09-16 17:45
    VLAI
    Title
    praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard)
    Summary
    PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256 signing key when PLATFORM_JWT_SECRET is unset, while the startup and token-issuance guards are disabled because PLATFORM_ENV also defaults to dev. An unauthenticated attacker can sign a JWT containing an attacker-chosen sub value, and AuthService._verify_token() accepts it as an authenticated identity, enabling user or workspace-owner impersonation when a target identifier is known. This vulnerability is fixed in praisonai-platform 0.1.6.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:45 UTC
    CWE
    • CWE-287 - Improper Authentication
    • CWE-798 - Use of Hard-coded Credentials
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57148",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:45:22.547557Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:45:28.460Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.51"
                }
              ]
            },
            {
              "product": "praisonai-platform",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.1.6"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256 signing key when PLATFORM_JWT_SECRET is unset, while the startup and token-issuance guards are disabled because PLATFORM_ENV also defaults to dev. An unauthenticated attacker can sign a JWT containing an attacker-chosen sub value, and AuthService._verify_token() accepts it as an authenticated identity, enabling user or workspace-owner impersonation when a target identifier is known. This vulnerability is fixed in praisonai-platform 0.1.6."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-287",
                  "description": "CWE-287: Improper Authentication",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-798",
                  "description": "CWE-798: Use of Hard-coded Credentials",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:32:22.525Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51"
            }
          ],
          "source": {
            "advisory": "GHSA-f38v-77qj-h4jq",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard)"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57148",
        "datePublished": "2026-09-15T10:32:22.525Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-16T17:45:28.460Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57147 (GCVE-0-2026-57147)

    Vulnerability from nvd – Published: 2026-09-15 10:34 – Updated: 2026-09-17 14:18
    VLAI
    Title
    praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery
    Summary
    PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to JWT_SECRET when PLATFORM_JWT_SECRET is unset, and its production guard does not run when PLATFORM_ENV is also unset because that setting defaults to dev. A remote unauthenticated attacker can mint an HS256 token with an arbitrary sub and email, and the platform's AuthService._verify_token() and get_current_user dependency accept the forged identity for protected API routes. This vulnerability is fixed in praisonai-platform 0.1.6.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:18 UTC
    CWE
    • CWE-798 - Use of Hard-coded Credentials
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57147",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:18:09.498050Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:18:35.600Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://www.youtube.com/watch?v=bDSRHAI28BY\u0026list=RDhqGkrTbgU2c\u0026index=8"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.51"
                }
              ]
            },
            {
              "product": "praisonai-platform",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.1.6"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to JWT_SECRET when PLATFORM_JWT_SECRET is unset, and its production guard does not run when PLATFORM_ENV is also unset because that setting defaults to dev. A remote unauthenticated attacker can mint an HS256 token with an arbitrary sub and email, and the platform\u0027s AuthService._verify_token() and get_current_user dependency accept the forged identity for protected API routes. This vulnerability is fixed in praisonai-platform 0.1.6."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-798",
                  "description": "CWE-798: Use of Hard-coded Credentials",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:34:16.300Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cwj8-7gp2-ggcw",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cwj8-7gp2-ggcw"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51"
            }
          ],
          "source": {
            "advisory": "GHSA-cwj8-7gp2-ggcw",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai-platform: default JWT signing secret \u0027dev-secret-change-me\u0027 enables token forgery"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57147",
        "datePublished": "2026-09-15T10:34:16.300Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-17T14:18:35.600Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57141 (GCVE-0-2026-57141)

    Vulnerability from nvd – Published: 2026-09-15 10:14 – Updated: 2026-09-15 13:52
    VLAI
    Title
    PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool
    Summary
    PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function() and with(sandbox), while a regular-expression blocklist can be bypassed with Function('return this')() to recover the global object and by constructing the child_process module name dynamically. An attacker who can influence the code argument can access host process capabilities, read or write files, obtain environment credentials, and execute operating-system commands with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 13:30 UTC
    CWE
    • CWE-94 - Improper Control of Generation of Code ('Code Injection')
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57141",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T13:30:37.824387Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T13:52:47.854Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function() and with(sandbox), while a regular-expression blocklist can be bypassed with Function(\u0027return this\u0027)() to recover the global object and by constructing the child_process module name dynamically. An attacker who can influence the code argument can access host process capabilities, read or write files, obtain environment credentials, and execute operating-system commands with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-94",
                  "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:14:16.721Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p69m-4f92-2v84",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p69m-4f92-2v84"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-p69m-4f92-2v84",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57141",
        "datePublished": "2026-09-15T10:14:16.721Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-15T13:52:47.854Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57140 (GCVE-0-2026-57140)

    Vulnerability from nvd – Published: 2026-09-15 10:26 – Updated: 2026-09-15 13:52
    VLAI
    Title
    PraisonAI AgentOS exposes unauthenticated agent listing and invocation
    Summary
    PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the service can obtain agent names, roles, and instruction prefixes and can invoke a selected agent, potentially reaching its tools, memory, external APIs, credentials, and workflow state. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 13:30 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.6.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57140",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T13:30:35.465013Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T13:52:34.686Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.6.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the service can obtain agent names, roles, and instruction prefixes and can invoke a selected agent, potentially reaching its tools, memory, external APIs, credentials, and workflow state. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 9.4,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:26:11.173Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9752-mhqh-h34f",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9752-mhqh-h34f"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-9752-mhqh-h34f",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI AgentOS exposes unauthenticated agent listing and invocation"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57140",
        "datePublished": "2026-09-15T10:26:11.173Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-15T13:52:34.686Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57139 (GCVE-0-2026-57139)

    Vulnerability from nvd – Published: 2026-09-15 10:25 – Updated: 2026-09-17 14:17
    VLAI
    Title
    PraisonAI MCPServer exposes unauthenticated HTTP tools/call
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:17 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-862 - Missing Authorization
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57139",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:17:03.942509Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:17:37.563Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:25:26.890Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-j4f3-55x4-r6q2",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI MCPServer exposes unauthenticated HTTP tools/call"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57139",
        "datePublished": "2026-09-15T10:25:26.890Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-17T14:17:37.563Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57138 (GCVE-0-2026-57138)

    Vulnerability from nvd – Published: 2026-09-15 10:22 – Updated: 2026-09-17 14:13
    VLAI
    Title
    PraisonAI codeMode sandbox escape via Function constructor
    Summary
    PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:12 UTC
    CWE
    • CWE-184 - Incomplete List of Disallowed Inputs
    • CWE-693 - Protection Mechanism Failure
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.4.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57138",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:12:03.702622Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:13:25.541Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.4.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.9,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-184",
                  "description": "CWE-184: Incomplete List of Disallowed Inputs",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:22:19.249Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-vmmj-pfw7-fjwp",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI codeMode sandbox escape via Function constructor"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57138",
        "datePublished": "2026-09-15T10:22:19.249Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-17T14:13:25.541Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57137 (GCVE-0-2026-57137)

    Vulnerability from nvd – Published: 2026-09-15 10:20 – Updated: 2026-09-15 12:46
    VLAI
    Title
    PraisonAI AgentLoop onToolCall approval runs after tool execution
    Summary
    PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:44 UTC
    CWE
    • CWE-693 - Protection Mechanism Failure
    • CWE-862 - Missing Authorization
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.4.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57137",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:44:54.123919Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:46:04.174Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.4.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:20:45.686Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-h2w2-v7j6-xqm4",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI AgentLoop onToolCall approval runs after tool execution"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57137",
        "datePublished": "2026-09-15T10:20:45.686Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-15T12:46:04.174Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57136 (GCVE-0-2026-57136)

    Vulnerability from nvd – Published: 2026-09-15 10:21 – Updated: 2026-09-15 12:40
    VLAI
    Title
    PraisonAI SandboxExecutor allowedCommands bypass via shell chaining
    Summary
    PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the first whitespace-delimited executable against allowedCommands, then SandboxExecutor passes the complete command string to sh -c. A command beginning with an allowed executable can append a non-allowlisted command through shell metacharacters, causing arbitrary commands to run with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:39 UTC
    CWE
    • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
    • CWE-693 - Protection Mechanism Failure
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.2.3, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57136",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:39:49.934747Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:40:32.718Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.2.3, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the first whitespace-delimited executable against allowedCommands, then SandboxExecutor passes the complete command string to sh -c. A command beginning with an allowed executable can append a non-allowlisted command through shell metacharacters, causing arbitrary commands to run with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-78",
                  "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:21:29.574Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-vjv9-7m7j-h833",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI SandboxExecutor allowedCommands bypass via shell chaining"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57136",
        "datePublished": "2026-09-15T10:21:29.574Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:40:32.718Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57135 (GCVE-0-2026-57135)

    Vulnerability from nvd – Published: 2026-09-15 10:23 – Updated: 2026-09-15 12:43
    VLAI
    Title
    PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients
    Summary
    PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts uses buildEnv() only to inject invalid http_proxy and https_proxy environment variables and does not establish an operating-system network boundary. Programs that ignore those proxy variables can open sockets directly, allowing supposedly isolated commands to reach localhost, internal services, cloud metadata, or external hosts and potentially exfiltrate data. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:43 UTC
    CWE
    • CWE-653 - Improper Isolation or Compartmentalization
    • CWE-693 - Protection Mechanism Failure
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.2.3, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57135",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:43:08.182873Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:43:30.886Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.2.3, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts uses buildEnv() only to inject invalid http_proxy and https_proxy environment variables and does not establish an operating-system network boundary. Programs that ignore those proxy variables can open sockets directly, allowing supposedly isolated commands to reach localhost, internal services, cloud metadata, or external hosts and potentially exfiltrate data. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 7.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-653",
                  "description": "CWE-653: Improper Isolation or Compartmentalization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:23:54.408Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-gqmf-56h7-rrpf",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57135",
        "datePublished": "2026-09-15T10:23:54.408Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:43:30.886Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57134 (GCVE-0-2026-57134)

    Vulnerability from nvd – Published: 2026-09-15 10:23 – Updated: 2026-09-15 12:37
    VLAI
    Title
    PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without calling auth.validate(), then return an authenticated result, allowing callers with invalid credentials to access MCP tools and resources protected by those policies. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:36 UTC
    CWE
    • CWE-287 - Improper Authentication
    • CWE-288 - Authentication Bypass Using an Alternate Path or Channel
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.1, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57134",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:36:39.614902Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:37:03.514Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.1, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without calling auth.validate(), then return an authenticated result, allowing callers with invalid credentials to access MCP tools and resources protected by those policies. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-287",
                  "description": "CWE-287: Improper Authentication",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-288",
                  "description": "CWE-288: Authentication Bypass Using an Alternate Path or Channel",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:23:11.557Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-4qq2-2j2x-x62c",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57134",
        "datePublished": "2026-09-15T10:23:11.557Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:37:03.514Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57133 (GCVE-0-2026-57133)

    Vulnerability from nvd – Published: 2026-09-15 10:24 – Updated: 2026-09-16 17:44
    VLAI
    Title
    PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:43 UTC
    CWE
    • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
    • CWE-693 - Protection Mechanism Failure
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.1, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57133",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:43:56.503486Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:44:02.031Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.1, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-78",
                  "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:24:37.405Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-5jv7-2mjm-h6qj",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57133",
        "datePublished": "2026-09-15T10:24:37.405Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-16T17:44:02.031Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57112 (GCVE-0-2026-57112)

    Vulnerability from nvd – Published: 2026-09-15 10:13 – Updated: 2026-09-16 17:51
    VLAI
    Title
    PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools
    Summary
    PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or authentication enforcement. A malicious website can use DNS rebinding against a reachable local or internal SSE server, supply attacker-controlled Host and Origin headers, enumerate registered tools, and invoke them with the server user's privileges. The Streamable HTTP transport rejects the same hostile Origin, which isolates the flaw to the legacy SSE wrapper. An initial remediation was released in praisonaiagents 1.6.59 and PraisonAI 4.6.59.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:51 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-346 - Origin Validation Error
    • CWE-862 - Missing Authorization
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57112",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:51:49.084581Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:51:54.611Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 3.10.0, \u003c 4.6.59"
                }
              ]
            },
            {
              "product": "praisonaiagents",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.6.0, \u003c 1.6.59"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or authentication enforcement. A malicious website can use DNS rebinding against a reachable local or internal SSE server, supply attacker-controlled Host and Origin headers, enumerate registered tools, and invoke them with the server user\u0027s privileges. The Streamable HTTP transport rejects the same hostile Origin, which isolates the flaw to the legacy SSE wrapper. An initial remediation was released in praisonaiagents 1.6.59 and PraisonAI 4.6.59."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.3,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-346",
                  "description": "CWE-346: Origin Validation Error",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:13:21.700Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59"
            }
          ],
          "source": {
            "advisory": "GHSA-vmf9-xx9w-86wx",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57112",
        "datePublished": "2026-09-15T10:13:21.700Z",
        "dateReserved": "2026-06-24T00:33:17.706Z",
        "dateUpdated": "2026-09-16T17:51:54.611Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57145 (GCVE-0-2026-57145)

    Vulnerability from nvd – Published: 2026-09-14 15:10 – Updated: 2026-09-14 18:11
    VLAI
    Title
    PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-14 17:11 UTC
    CWE
    • CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.62
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57145",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-14T17:11:01.278711Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-14T18:11:30.131Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.62"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 9.1,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-22",
                  "description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:10:45.705Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-29w3-p9w9-wc47",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-29w3-p9w9-wc47"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-29w3-p9w9-wc47",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57145",
        "datePublished": "2026-09-14T15:10:45.705Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-14T18:11:30.131Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57132 (GCVE-0-2026-57132)

    Vulnerability from nvd – Published: 2026-09-14 15:09 – Updated: 2026-09-16 15:09
    VLAI
    Title
    PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/invoke without CALL_SERVER_TOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their connected tools or private context to unauthenticated invocation. The vulnerability is fixed in 4.6.62.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 15:09 UTC
    CWE
    • CWE-287 - Improper Authentication
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.62
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57132",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T15:09:05.722791Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T15:09:30.644Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8ccj-p46r-jwqq"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.62"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/invoke without CALL_SERVER_TOKEN authentication. Deployments that use the application\u0027s advertised opt-out can expose registered agents and their connected tools or private context to unauthenticated invocation. The vulnerability is fixed in 4.6.62."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-287",
                  "description": "CWE-287: Improper Authentication",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:09:19.782Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8ccj-p46r-jwqq",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-8ccj-p46r-jwqq"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-8ccj-p46r-jwqq",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57132",
        "datePublished": "2026-09-14T15:09:19.782Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-16T15:09:30.644Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57131 (GCVE-0-2026-57131)

    Vulnerability from nvd – Published: 2026-09-14 15:06 – Updated: 2026-09-14 16:28
    VLAI
    Title
    praisonai: Jobs API exposes agent-execution endpoints with no authentication
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.create_app mounts praisonai.jobs.router.create_router under /api/v1/runs without authentication or per-job authorization. Network clients can submit attacker-controlled prompts and agent configuration, list and read jobs, stream results, and cancel or delete other jobs, exposing service credentials and connected tool capabilities to unauthorized agent execution. This vulnerability is fixed in 4.6.58.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-14 16:27 UTC
    CWE
    • CWE-94 - Improper Control of Generation of Code ('Code Injection')
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-862 - Missing Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.48
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57131",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-14T16:27:42.909723Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-14T16:28:08.459Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fq2m-6wqh-x44g"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.48"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.create_app mounts praisonai.jobs.router.create_router under /api/v1/runs without authentication or per-job authorization. Network clients can submit attacker-controlled prompts and agent configuration, list and read jobs, stream results, and cancel or delete other jobs, exposing service credentials and connected tool capabilities to unauthorized agent execution. This vulnerability is fixed in 4.6.58."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-94",
                  "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:06:20.246Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fq2m-6wqh-x44g",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-fq2m-6wqh-x44g"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58"
            }
          ],
          "source": {
            "advisory": "GHSA-fq2m-6wqh-x44g",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai: Jobs API exposes agent-execution endpoints with no authentication"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57131",
        "datePublished": "2026-09-14T15:06:20.246Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-14T16:28:08.459Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57127 (GCVE-0-2026-57127)

    Vulnerability from nvd – Published: 2026-09-14 15:01 – Updated: 2026-09-14 16:47
    VLAI
    Title
    praisonai: recipe serve auth middleware silently disables itself when no secret is set
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.58, recipe serve installs APIKeyAuthMiddleware or JWTAuthMiddleware when an operator selects api-key or JWT authentication, but each middleware forwards requests when PRAISONAI_API_KEY or PRAISONAI_JWT_SECRET and the corresponding recipe value are absent. Unauthenticated clients can then reach recipe execution, input, and output surfaces and may trigger connected tools despite the operator explicitly enabling authentication. This issue is fixed in 4.6.58.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-14 16:46 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.48
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57127",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-14T16:46:54.383926Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-14T16:47:18.317Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4hj-7hfh-g2f4"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.48"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.58, recipe serve installs APIKeyAuthMiddleware or JWTAuthMiddleware when an operator selects api-key or JWT authentication, but each middleware forwards requests when PRAISONAI_API_KEY or PRAISONAI_JWT_SECRET and the corresponding recipe value are absent. Unauthenticated clients can then reach recipe execution, input, and output surfaces and may trigger connected tools despite the operator explicitly enabling authentication. This issue is fixed in 4.6.58."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:01:48.781Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4hj-7hfh-g2f4",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4hj-7hfh-g2f4"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58"
            }
          ],
          "source": {
            "advisory": "GHSA-j4hj-7hfh-g2f4",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai: recipe serve auth middleware silently disables itself when no secret is set"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57127",
        "datePublished": "2026-09-14T15:01:48.781Z",
        "dateReserved": "2026-06-24T00:33:17.707Z",
        "dateUpdated": "2026-09-14T16:47:18.317Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57124 (GCVE-0-2026-57124)

    Vulnerability from nvd – Published: 2026-09-14 15:04 – Updated: 2026-09-14 19:02
    VLAI
    Title
    PraisonAI UI MCP connect endpoint allows unauthenticated local command execution
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands bind to 0.0.0.0 by default, a reachable unauthenticated client can execute commands as the UI service account even when the MCP handshake later fails. This vulnerability is fixed in 4.6.59.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-14 19:02 UTC
    CWE
    • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
    • CWE-306 - Missing Authentication for Critical Function
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.59
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57124",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-14T19:02:29.151503Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-14T19:02:35.012Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p75f-6fp4-p57w"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.59"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands bind to 0.0.0.0 by default, a reachable unauthenticated client can execute commands as the UI service account even when the MCP handshake later fails. This vulnerability is fixed in 4.6.59."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-78",
                  "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:04:54.198Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p75f-6fp4-p57w",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p75f-6fp4-p57w"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59"
            }
          ],
          "source": {
            "advisory": "GHSA-p75f-6fp4-p57w",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI UI MCP connect endpoint allows unauthenticated local command execution"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57124",
        "datePublished": "2026-09-14T15:04:54.198Z",
        "dateReserved": "2026-06-24T00:33:17.707Z",
        "dateUpdated": "2026-09-14T19:02:35.012Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57122 (GCVE-0-2026-57122)

    Vulnerability from nvd – Published: 2026-09-14 15:02 – Updated: 2026-09-14 18:11
    VLAI
    Title
    PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp & Linear bots)
    Summary
    PraisonAI is a multi-agent teams system. Prior to 4.6.59, the WhatsApp and Linear bot webhook handlers verify HMAC signatures only when WHATSAPP_APP_SECRET or LINEAR_WEBHOOK_SECRET is configured and otherwise parse and dispatch unsigned request bodies. A remote unauthenticated client that reaches the webhook route can forge messages, comments, or agent-session events, impersonate platform users, influence agent prompts and actions, and disrupt bot processing. This issue is fixed in 4.6.59.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-14 17:06 UTC
    CWE
    • CWE-345 - Insufficient Verification of Data Authenticity
    • CWE-347 - Improper Verification of Cryptographic Signature
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 4.6.59
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57122",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-14T17:06:07.666555Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-14T18:11:37.800Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.59"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 4.6.59, the WhatsApp and Linear bot webhook handlers verify HMAC signatures only when WHATSAPP_APP_SECRET or LINEAR_WEBHOOK_SECRET is configured and otherwise parse and dispatch unsigned request bodies. A remote unauthenticated client that reaches the webhook route can forge messages, comments, or agent-session events, impersonate platform users, influence agent prompts and actions, and disrupt bot processing. This issue is fixed in 4.6.59."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 8.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "LOW",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-345",
                  "description": "CWE-345: Insufficient Verification of Data Authenticity",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-347",
                  "description": "CWE-347: Improper Verification of Cryptographic Signature",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-14T15:02:43.754Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-x92v-rpx6-p6cw",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-x92v-rpx6-p6cw"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59"
            }
          ],
          "source": {
            "advisory": "GHSA-x92v-rpx6-p6cw",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp \u0026 Linear bots)"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57122",
        "datePublished": "2026-09-14T15:02:43.754Z",
        "dateReserved": "2026-06-24T00:33:17.707Z",
        "dateUpdated": "2026-09-14T18:11:37.800Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57147 (GCVE-0-2026-57147)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:34 – Updated: 2026-09-17 14:18
    VLAI
    Title
    praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery
    Summary
    PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to JWT_SECRET when PLATFORM_JWT_SECRET is unset, and its production guard does not run when PLATFORM_ENV is also unset because that setting defaults to dev. A remote unauthenticated attacker can mint an HS256 token with an arbitrary sub and email, and the platform's AuthService._verify_token() and get_current_user dependency accept the forged identity for protected API routes. This vulnerability is fixed in praisonai-platform 0.1.6.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:18 UTC
    CWE
    • CWE-798 - Use of Hard-coded Credentials
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57147",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:18:09.498050Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:18:35.600Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://www.youtube.com/watch?v=bDSRHAI28BY\u0026list=RDhqGkrTbgU2c\u0026index=8"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.51"
                }
              ]
            },
            {
              "product": "praisonai-platform",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.1.6"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to JWT_SECRET when PLATFORM_JWT_SECRET is unset, and its production guard does not run when PLATFORM_ENV is also unset because that setting defaults to dev. A remote unauthenticated attacker can mint an HS256 token with an arbitrary sub and email, and the platform\u0027s AuthService._verify_token() and get_current_user dependency accept the forged identity for protected API routes. This vulnerability is fixed in praisonai-platform 0.1.6."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-798",
                  "description": "CWE-798: Use of Hard-coded Credentials",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:34:16.300Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cwj8-7gp2-ggcw",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-cwj8-7gp2-ggcw"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51"
            }
          ],
          "source": {
            "advisory": "GHSA-cwj8-7gp2-ggcw",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai-platform: default JWT signing secret \u0027dev-secret-change-me\u0027 enables token forgery"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57147",
        "datePublished": "2026-09-15T10:34:16.300Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-17T14:18:35.600Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57148 (GCVE-0-2026-57148)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:32 – Updated: 2026-09-16 17:45
    VLAI
    Title
    praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard)
    Summary
    PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256 signing key when PLATFORM_JWT_SECRET is unset, while the startup and token-issuance guards are disabled because PLATFORM_ENV also defaults to dev. An unauthenticated attacker can sign a JWT containing an attacker-chosen sub value, and AuthService._verify_token() accepts it as an authenticated identity, enabling user or workspace-owner impersonation when a target identifier is known. This vulnerability is fixed in praisonai-platform 0.1.6.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:45 UTC
    CWE
    • CWE-287 - Improper Authentication
    • CWE-798 - Use of Hard-coded Credentials
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57148",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:45:22.547557Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:45:28.460Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 4.6.51"
                }
              ]
            },
            {
              "product": "praisonai-platform",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.1.6"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256 signing key when PLATFORM_JWT_SECRET is unset, while the startup and token-issuance guards are disabled because PLATFORM_ENV also defaults to dev. An unauthenticated attacker can sign a JWT containing an attacker-chosen sub value, and AuthService._verify_token() accepts it as an authenticated identity, enabling user or workspace-owner impersonation when a target identifier is known. This vulnerability is fixed in praisonai-platform 0.1.6."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-287",
                  "description": "CWE-287: Improper Authentication",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-798",
                  "description": "CWE-798: Use of Hard-coded Credentials",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:32:22.525Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f38v-77qj-h4jq"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/pull/1793",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/pull/1793"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.51"
            }
          ],
          "source": {
            "advisory": "GHSA-f38v-77qj-h4jq",
            "discovery": "UNKNOWN"
          },
          "title": "praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard)"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57148",
        "datePublished": "2026-09-15T10:32:22.525Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-16T17:45:28.460Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57140 (GCVE-0-2026-57140)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:26 – Updated: 2026-09-15 13:52
    VLAI
    Title
    PraisonAI AgentOS exposes unauthenticated agent listing and invocation
    Summary
    PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the service can obtain agent names, roles, and instruction prefixes and can invoke a selected agent, potentially reaching its tools, memory, external APIs, credentials, and workflow state. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 13:30 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.6.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57140",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T13:30:35.465013Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T13:52:34.686Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.6.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the service can obtain agent names, roles, and instruction prefixes and can invoke a selected agent, potentially reaching its tools, memory, external APIs, credentials, and workflow state. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 9.4,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:26:11.173Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9752-mhqh-h34f",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9752-mhqh-h34f"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-9752-mhqh-h34f",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI AgentOS exposes unauthenticated agent listing and invocation"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57140",
        "datePublished": "2026-09-15T10:26:11.173Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-15T13:52:34.686Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57139 (GCVE-0-2026-57139)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:25 – Updated: 2026-09-17 14:17
    VLAI
    Title
    PraisonAI MCPServer exposes unauthenticated HTTP tools/call
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:17 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-862 - Missing Authorization
    • CWE-1188 - Insecure Default Initialization of Resource
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57139",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:17:03.942509Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:17:37.563Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction and forwards every HTTP POST request to handleRequest() without authentication or authorization. Any network client that can reach the port can call tools/list, tools/call, resources/read, or prompts/get, causing registered handlers to run with server-side credentials and process privileges or disclose registered data. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1188",
                  "description": "CWE-1188: Insecure Default Initialization of Resource",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:25:26.890Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j4f3-55x4-r6q2"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-j4f3-55x4-r6q2",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI MCPServer exposes unauthenticated HTTP tools/call"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57139",
        "datePublished": "2026-09-15T10:25:26.890Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-17T14:17:37.563Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57133 (GCVE-0-2026-57133)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:24 – Updated: 2026-09-16 17:44
    VLAI
    Title
    PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:43 UTC
    CWE
    • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
    • CWE-693 - Protection Mechanism Failure
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.1, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57133",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:43:56.503486Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:44:02.031Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.1, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-78",
                  "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:24:37.405Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-5jv7-2mjm-h6qj",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57133",
        "datePublished": "2026-09-15T10:24:37.405Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-16T17:44:02.031Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57135 (GCVE-0-2026-57135)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:23 – Updated: 2026-09-15 12:43
    VLAI
    Title
    PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients
    Summary
    PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts uses buildEnv() only to inject invalid http_proxy and https_proxy environment variables and does not establish an operating-system network boundary. Programs that ignore those proxy variables can open sockets directly, allowing supposedly isolated commands to reach localhost, internal services, cloud metadata, or external hosts and potentially exfiltrate data. An initial remediation was released in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:43 UTC
    CWE
    • CWE-653 - Improper Isolation or Compartmentalization
    • CWE-693 - Protection Mechanism Failure
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.2.3, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57135",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:43:08.182873Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:43:30.886Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.2.3, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts uses buildEnv() only to inject invalid http_proxy and https_proxy environment variables and does not establish an operating-system network boundary. Programs that ignore those proxy variables can open sockets directly, allowing supposedly isolated commands to reach localhost, internal services, cloud metadata, or external hosts and potentially exfiltrate data. An initial remediation was released in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 7.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-653",
                  "description": "CWE-653: Improper Isolation or Compartmentalization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:23:54.408Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gqmf-56h7-rrpf"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-gqmf-56h7-rrpf",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57135",
        "datePublished": "2026-09-15T10:23:54.408Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:43:30.886Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57134 (GCVE-0-2026-57134)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:23 – Updated: 2026-09-15 12:37
    VLAI
    Title
    PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation
    Summary
    PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without calling auth.validate(), then return an authenticated result, allowing callers with invalid credentials to access MCP tools and resources protected by those policies. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:36 UTC
    CWE
    • CWE-287 - Improper Authentication
    • CWE-288 - Authentication Bypass Using an Alternate Path or Channel
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.5.1, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57134",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:36:39.614902Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:37:03.514Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.5.1, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without calling auth.validate(), then return an authenticated result, allowing callers with invalid credentials to access MCP tools and resources protected by those policies. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-287",
                  "description": "CWE-287: Improper Authentication",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-288",
                  "description": "CWE-288: Authentication Bypass Using an Alternate Path or Channel",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:23:11.557Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4qq2-2j2x-x62c"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-4qq2-2j2x-x62c",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57134",
        "datePublished": "2026-09-15T10:23:11.557Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:37:03.514Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57138 (GCVE-0-2026-57138)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:22 – Updated: 2026-09-17 14:13
    VLAI
    Title
    PraisonAI codeMode sandbox escape via Function constructor
    Summary
    PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-17 14:12 UTC
    CWE
    • CWE-184 - Incomplete List of Disallowed Inputs
    • CWE-693 - Protection Mechanism Failure
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.4.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57138",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-17T14:12:03.702622Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-17T14:13:25.541Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.4.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.9,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-184",
                  "description": "CWE-184: Incomplete List of Disallowed Inputs",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:22:19.249Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-vmmj-pfw7-fjwp",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI codeMode sandbox escape via Function constructor"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57138",
        "datePublished": "2026-09-15T10:22:19.249Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-17T14:13:25.541Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57136 (GCVE-0-2026-57136)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:21 – Updated: 2026-09-15 12:40
    VLAI
    Title
    PraisonAI SandboxExecutor allowedCommands bypass via shell chaining
    Summary
    PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the first whitespace-delimited executable against allowedCommands, then SandboxExecutor passes the complete command string to sh -c. A command beginning with an allowed executable can append a non-allowlisted command through shell metacharacters, causing arbitrary commands to run with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:39 UTC
    CWE
    • CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
    • CWE-693 - Protection Mechanism Failure
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.2.3, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57136",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:39:49.934747Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:40:32.718Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.2.3, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the first whitespace-delimited executable against allowedCommands, then SandboxExecutor passes the complete command string to sh -c. A command beginning with an allowed executable can append a non-allowlisted command through shell metacharacters, causing arbitrary commands to run with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-78",
                  "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:21:29.574Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vjv9-7m7j-h833"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-vjv9-7m7j-h833",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI SandboxExecutor allowedCommands bypass via shell chaining"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57136",
        "datePublished": "2026-09-15T10:21:29.574Z",
        "dateReserved": "2026-06-24T00:33:17.708Z",
        "dateUpdated": "2026-09-15T12:40:32.718Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57137 (GCVE-0-2026-57137)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:20 – Updated: 2026-09-15 12:46
    VLAI
    Title
    PraisonAI AgentLoop onToolCall approval runs after tool execution
    Summary
    PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 12:44 UTC
    CWE
    • CWE-693 - Protection Mechanism Failure
    • CWE-862 - Missing Authorization
    • CWE-863 - Incorrect Authorization
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: >= 1.4.0, < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57137",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T12:44:54.123919Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T12:46:04.174Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.4.0, \u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.8,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-693",
                  "description": "CWE-693: Protection Mechanism Failure",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-863",
                  "description": "CWE-863: Incorrect Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:20:45.686Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62"
            }
          ],
          "source": {
            "advisory": "GHSA-h2w2-v7j6-xqm4",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI AgentLoop onToolCall approval runs after tool execution"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57137",
        "datePublished": "2026-09-15T10:20:45.686Z",
        "dateReserved": "2026-06-24T01:45:48.696Z",
        "dateUpdated": "2026-09-15T12:46:04.174Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57141 (GCVE-0-2026-57141)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:14 – Updated: 2026-09-15 13:52
    VLAI
    Title
    PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool
    Summary
    PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function() and with(sandbox), while a regular-expression blocklist can be bypassed with Function('return this')() to recover the global object and by constructing the child_process module name dynamically. An attacker who can influence the code argument can access host process capabilities, read or write files, obtain environment credentials, and execute operating-system commands with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-15 13:30 UTC
    CWE
    • CWE-94 - Improper Control of Generation of Code ('Code Injection')
    Impacted products
    Vendor Product Version
    MervinPraison PraisonAI Affected: < 1.7.2
    Create a notification for this product.
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57141",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-15T13:30:37.824387Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-15T13:52:47.854Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 1.7.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function() and with(sandbox), while a regular-expression blocklist can be bypassed with Function(\u0027return this\u0027)() to recover the global object and by constructing the child_process module name dynamically. An attacker who can influence the code argument can access host process capabilities, read or write files, obtain environment credentials, and execute operating-system commands with the PraisonAI process privileges. This issue is fixed in version 1.7.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 9.8,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-94",
                  "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:14:16.721Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p69m-4f92-2v84",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p69m-4f92-2v84"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60"
            }
          ],
          "source": {
            "advisory": "GHSA-p69m-4f92-2v84",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57141",
        "datePublished": "2026-09-15T10:14:16.721Z",
        "dateReserved": "2026-06-24T01:45:48.697Z",
        "dateUpdated": "2026-09-15T13:52:47.854Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-57112 (GCVE-0-2026-57112)

    Vulnerability from cvelistv5 – Published: 2026-09-15 10:13 – Updated: 2026-09-16 17:51
    VLAI
    Title
    PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools
    Summary
    PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or authentication enforcement. A malicious website can use DNS rebinding against a reachable local or internal SSE server, supply attacker-controlled Host and Origin headers, enumerate registered tools, and invoke them with the server user's privileges. The Streamable HTTP transport rejects the same hostile Origin, which isolates the flaw to the legacy SSE wrapper. An initial remediation was released in praisonaiagents 1.6.59 and PraisonAI 4.6.59.
    SSVC
    Exploitation: poc Automatable: no Technical Impact: total
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-09-16 17:51 UTC
    CWE
    • CWE-306 - Missing Authentication for Critical Function
    • CWE-346 - Origin Validation Error
    • CWE-862 - Missing Authorization
    Impacted products
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-57112",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-09-16T17:51:49.084581Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-09-16T17:51:54.611Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "PraisonAI",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 3.10.0, \u003c 4.6.59"
                }
              ]
            },
            {
              "product": "praisonaiagents",
              "vendor": "MervinPraison",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 0.6.0, \u003c 1.6.59"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or authentication enforcement. A malicious website can use DNS rebinding against a reachable local or internal SSE server, supply attacker-controlled Host and Origin headers, enumerate registered tools, and invoke them with the server user\u0027s privileges. The Streamable HTTP transport rejects the same hostile Origin, which isolates the flaw to the legacy SSE wrapper. An initial remediation was released in praisonaiagents 1.6.59 and PraisonAI 4.6.59."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 8.3,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-306",
                  "description": "CWE-306: Missing Authentication for Critical Function",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-346",
                  "description": "CWE-346: Origin Validation Error",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-862",
                  "description": "CWE-862: Missing Authorization",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-09-15T10:13:21.700Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9"
            },
            {
              "name": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59"
            }
          ],
          "source": {
            "advisory": "GHSA-vmf9-xx9w-86wx",
            "discovery": "UNKNOWN"
          },
          "title": "PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-57112",
        "datePublished": "2026-09-15T10:13:21.700Z",
        "dateReserved": "2026-06-24T00:33:17.706Z",
        "dateUpdated": "2026-09-16T17:51:54.611Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }