Vulnerability-Lookup

CVE-2026-55743 (GCVE-0-2026-55743)

Vulnerability from cvelistv5 – Published: 2026-06-17 14:08 – Updated: 2026-08-10 11:44

Title

OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution

Summary

Severity

9.6 (Critical)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

9.4 (Critical)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

SSVC

Exploitation: none Automatable: no Technical Impact: total

CISA Coordinator (v2.0.3)

CWE

CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CWE-184 - Incomplete List of Disallowed Inputs

Assigner

TuranSec

References

3 references

URL	Tags
https://github.com/tinyhumansai/openhuman/commit/…	patch
https://github.com/tinyhumansai/openhuman/blob/v0…	technical-description
https://github.com/tinyhumansai/openhuman	product

Impacted products

1 product

Vendor	Product	Version
tinyhumansai	OpenHuman	Affected: 0 , ≤ 0.54.0 (semver)

Date Public

2026-06-17 14:08

Credits

Bobur Abdugafforov Zikrillayev Salohiddin

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-55743",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-17T15:40:33.751475Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-17T15:40:47.796Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "collectionURL": "https://github.com/tinyhumansai/openhuman",
          "defaultStatus": "unaffected",
          "platforms": [
            "macOS",
            "Windows",
            "Linux"
          ],
          "product": "OpenHuman",
          "programFiles": [
            "src/openhuman/security/policy.rs"
          ],
          "programRoutines": [
            {
              "name": "is_args_safe"
            },
            {
              "name": "skip_env_assignments"
            }
          ],
          "repo": "https://github.com/tinyhumansai/openhuman",
          "vendor": "tinyhumansai",
          "versions": [
            {
              "lessThanOrEqual": "0.54.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Bobur Abdugafforov"
        },
        {
          "lang": "en",
          "type": "analyst",
          "value": "Zikrillayev Salohiddin"
        }
      ],
      "datePublic": "2026-06-17T14:08:33.726Z",
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "\u003cp\u003eThe shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user.\u003c/p\u003e"
            }
          ],
          "value": "The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 9.6,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 9.4,
            "baseSeverity": "CRITICAL",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "PASSIVE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "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-184",
              "description": "CWE-184 Incomplete List of Disallowed Inputs",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-10T11:44:25.190Z",
        "orgId": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
        "shortName": "TuranSec"
      },
      "references": [
        {
          "name": "Fix commit (PR #2636): block find -execdir/-okdir",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7"
        },
        {
          "name": "Vulnerable source at v0.53.49-staging: src/openhuman/security/policy.rs",
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/tinyhumansai/openhuman"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "title": "OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
    "assignerShortName": "TuranSec",
    "cveId": "CVE-2026-55743",
    "datePublished": "2026-06-17T14:08:33.726Z",
    "dateReserved": "2026-06-17T12:59:17.621Z",
    "dateUpdated": "2026-08-10T11:44:25.190Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-55743",
      "date": "2026-08-10",
      "epss": "0.00704",
      "percentile": "0.49877"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-55743\",\"sourceIdentifier\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\",\"published\":\"2026-06-17T15:17:02.337\",\"lastModified\":\"2026-08-10T12:17:18.963\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user.\"}],\"affected\":[{\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\",\"affectedData\":[{\"vendor\":\"tinyhumansai\",\"product\":\"OpenHuman\",\"defaultStatus\":\"unaffected\",\"collectionURL\":\"https://github.com/tinyhumansai/openhuman\",\"platforms\":[\"macOS\",\"Windows\",\"Linux\"],\"programFiles\":[\"src/openhuman/security/policy.rs\"],\"programRoutines\":[{\"name\":\"is_args_safe\"},{\"name\":\"skip_env_assignments\"}],\"repo\":\"https://github.com/tinyhumansai/openhuman\",\"versions\":[{\"version\":\"0\",\"lessThanOrEqual\":\"0.54.0\",\"versionType\":\"semver\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X\",\"baseScore\":9.4,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"PASSIVE\",\"vulnConfidentialityImpact\":\"HIGH\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"HIGH\",\"subConfidentialityImpact\":\"HIGH\",\"subIntegrityImpact\":\"HIGH\",\"subAvailabilityImpact\":\"HIGH\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}],\"cvssMetricV31\":[{\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\",\"baseScore\":9.6,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":6.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-06-17T15:40:33.751475Z\",\"id\":\"CVE-2026-55743\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-78\"},{\"lang\":\"en\",\"value\":\"CWE-184\"}]}],\"references\":[{\"url\":\"https://github.com/tinyhumansai/openhuman\",\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\"},{\"url\":\"https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs\",\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\"},{\"url\":\"https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7\",\"source\":\"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-55743\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-06-17T15:40:33.751475Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-06-17T15:40:42.467Z\"}}], \"cna\": {\"title\": \"OpenHuman desktop agent shell tool sandbox bypass leads to arbitrary command execution\", \"source\": {\"discovery\": \"EXTERNAL\"}, \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Bobur Abdugafforov\"}, {\"lang\": \"en\", \"type\": \"analyst\", \"value\": \"Zikrillayev Salohiddin\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 9.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}, {\"format\": \"CVSS\", \"cvssV4_0\": {\"Safety\": \"NOT_DEFINED\", \"version\": \"4.0\", \"Recovery\": \"NOT_DEFINED\", \"baseScore\": 9.4, \"Automatable\": \"NOT_DEFINED\", \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"valueDensity\": \"NOT_DEFINED\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H\", \"exploitMaturity\": \"NOT_DEFINED\", \"providerUrgency\": \"NOT_DEFINED\", \"userInteraction\": \"PASSIVE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"HIGH\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"HIGH\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"HIGH\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnerabilityResponseEffort\": \"NOT_DEFINED\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"repo\": \"https://github.com/tinyhumansai/openhuman\", \"vendor\": \"tinyhumansai\", \"product\": \"OpenHuman\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"versionType\": \"semver\", \"lessThanOrEqual\": \"0.54.0\"}], \"platforms\": [\"macOS\", \"Windows\", \"Linux\"], \"programFiles\": [\"src/openhuman/security/policy.rs\"], \"collectionURL\": \"https://github.com/tinyhumansai/openhuman\", \"defaultStatus\": \"unaffected\", \"programRoutines\": [{\"name\": \"is_args_safe\"}, {\"name\": \"skip_env_assignments\"}]}], \"datePublic\": \"2026-06-17T14:08:33.726Z\", \"references\": [{\"url\": \"https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7\", \"name\": \"Fix commit (PR #2636): block find -execdir/-okdir\", \"tags\": [\"patch\"]}, {\"url\": \"https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs\", \"name\": \"Vulnerable source at v0.53.49-staging: src/openhuman/security/policy.rs\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/tinyhumansai/openhuman\", \"tags\": [\"product\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user.\", \"supportingMedia\": [{\"type\": \"text/html\", \"value\": \"\u003cp\u003eThe shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user.\u003c/p\u003e\", \"base64\": false}]}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-78\", \"description\": \"CWE-78 Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-184\", \"description\": \"CWE-184 Incomplete List of Disallowed Inputs\"}]}], \"providerMetadata\": {\"orgId\": \"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\", \"shortName\": \"TuranSec\", \"dateUpdated\": \"2026-08-10T11:44:25.190Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-55743\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-10T11:44:25.190Z\", \"dateReserved\": \"2026-06-17T12:59:17.621Z\", \"assignerOrgId\": \"309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c\", \"datePublished\": \"2026-06-17T14:08:33.726Z\", \"assignerShortName\": \"TuranSec\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-55743

Vulnerability from fkie_nvd - Published: 2026-06-17 15:17 - Updated: 2026-06-17 17:17

Severity

9.6 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

Summary

The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user. Two flaws in src/openhuman/security/policy.rs combine: (1) is_args_safe() blocks the find flags -exec and -ok but not the functionally identical -execdir and -okdir, which also execute an arbitrary command for each matched file; and (2) skip_env_assignments() strips leading inline KEY=value environment-variable assignments before allowlist validation, so a command such as GIT_EXTERNAL_DIFF=<cmd> git diff is validated as the allowed git diff but, when executed via the shell, runs <cmd> through git's environment-driven hooks (for example GIT_EXTERNAL_DIFF or GIT_SSH_COMMAND). Because the sandbox is the primary trust boundary between untrusted LLM-processed content and the host operating system, an attacker can achieve remote code execution via indirect prompt injection: a malicious document, email, calendar event, or web page ingested by the agent instructs it to run a benign-looking allowlisted command, resulting in arbitrary command execution, data exfiltration, arbitrary file read/write, and lateral movement on the user's machine. The issue was fixed in commit 60050aa09a870f53ed7e4cd40ed41fd2860329e7 (first released in 0.54.22-staging; first stable release 0.56.0), which blocks -execdir/-okdir for find.

References

	URL	Tags
	309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c	https://github.com/tinyhumansai/openhuman
	309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c	https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs
	309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c	https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "collectionURL": "https://github.com/tinyhumansai/openhuman",
          "defaultStatus": "unaffected",
          "platforms": [
            "macOS",
            "Windows",
            "Linux"
          ],
          "product": "OpenHuman",
          "programFiles": [
            "src/openhuman/security/policy.rs"
          ],
          "programRoutines": [
            {
              "name": "is_args_safe"
            },
            {
              "name": "skip_env_assignments"
            }
          ],
          "repo": "https://github.com/tinyhumansai/openhuman",
          "vendor": "tinyhumansai",
          "versions": [
            {
              "lessThanOrEqual": "0.54.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user. Two flaws in src/openhuman/security/policy.rs combine: (1) is_args_safe() blocks the find flags -exec and -ok but not the functionally identical -execdir and -okdir, which also execute an arbitrary command for each matched file; and (2) skip_env_assignments() strips leading inline KEY=value environment-variable assignments before allowlist validation, so a command such as GIT_EXTERNAL_DIFF=\u003ccmd\u003e git diff is validated as the allowed git diff but, when executed via the shell, runs \u003ccmd\u003e through git\u0027s environment-driven hooks (for example GIT_EXTERNAL_DIFF or GIT_SSH_COMMAND). Because the sandbox is the primary trust boundary between untrusted LLM-processed content and the host operating system, an attacker can achieve remote code execution via indirect prompt injection: a malicious document, email, calendar event, or web page ingested by the agent instructs it to run a benign-looking allowlisted command, resulting in arbitrary command execution, data exfiltration, arbitrary file read/write, and lateral movement on the user\u0027s machine. The issue was fixed in commit 60050aa09a870f53ed7e4cd40ed41fd2860329e7 (first released in 0.54.22-staging; first stable release 0.56.0), which blocks -execdir/-okdir for find."
    }
  ],
  "id": "CVE-2026-55743",
  "lastModified": "2026-06-17T17:17:27.580",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 9.6,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "CHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 6.0,
        "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
        "type": "Secondary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 9.4,
          "baseSeverity": "CRITICAL",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "NONE",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "HIGH",
          "subConfidentialityImpact": "HIGH",
          "subIntegrityImpact": "HIGH",
          "userInteraction": "PASSIVE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "HIGH",
          "vulnIntegrityImpact": "HIGH",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-55743",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-06-17T15:40:33.751475Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-06-17T15:17:02.337",
  "references": [
    {
      "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
      "url": "https://github.com/tinyhumansai/openhuman"
    },
    {
      "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
      "url": "https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs"
    },
    {
      "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
      "url": "https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7"
    }
  ],
  "sourceIdentifier": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-78"
        },
        {
          "lang": "en",
          "value": "CWE-184"
        }
      ],
      "source": "309f9ea4-e3e9-4c6c-b79d-e8eb01244f2c",
      "type": "Secondary"
    }
  ]
}

GHSA-34J2-GCWP-VRV5

Vulnerability from github – Published: 2026-06-17 18:35 – Updated: 2026-06-17 18:35

Details

The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user. Two flaws in src/openhuman/security/policy.rs combine: (1) is_args_safe() blocks the find flags -exec and -ok but not the functionally identical -execdir and -okdir, which also execute an arbitrary command for each matched file; and (2) skip_env_assignments() strips leading inline KEY=value environment-variable assignments before allowlist validation, so a command such as GIT_EXTERNAL_DIFF= git diff is validated as the allowed git diff but, when executed via the shell, runs through git's environment-driven hooks (for example GIT_EXTERNAL_DIFF or GIT_SSH_COMMAND). Because the sandbox is the primary trust boundary between untrusted LLM-processed content and the host operating system, an attacker can achieve remote code execution via indirect prompt injection: a malicious document, email, calendar event, or web page ingested by the agent instructs it to run a benign-looking allowlisted command, resulting in arbitrary command execution, data exfiltration, arbitrary file read/write, and lateral movement on the user's machine. The issue was fixed in commit 60050aa09a870f53ed7e4cd40ed41fd2860329e7 (first released in 0.54.22-staging; first stable release 0.56.0), which blocks -execdir/-okdir for find.

Severity

9.6 (Critical)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

9.4 (Critical)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-55743"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-78"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-06-17T15:17:02Z",
    "severity": "CRITICAL"
  },
  "details": "The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileges of the desktop user. Two flaws in src/openhuman/security/policy.rs combine: (1) is_args_safe() blocks the find flags -exec and -ok but not the functionally identical -execdir and -okdir, which also execute an arbitrary command for each matched file; and (2) skip_env_assignments() strips leading inline KEY=value environment-variable assignments before allowlist validation, so a command such as GIT_EXTERNAL_DIFF=\u003ccmd\u003e git diff is validated as the allowed git diff but, when executed via the shell, runs \u003ccmd\u003e through git\u0027s environment-driven hooks (for example GIT_EXTERNAL_DIFF or GIT_SSH_COMMAND). Because the sandbox is the primary trust boundary between untrusted LLM-processed content and the host operating system, an attacker can achieve remote code execution via indirect prompt injection: a malicious document, email, calendar event, or web page ingested by the agent instructs it to run a benign-looking allowlisted command, resulting in arbitrary command execution, data exfiltration, arbitrary file read/write, and lateral movement on the user\u0027s machine. The issue was fixed in commit 60050aa09a870f53ed7e4cd40ed41fd2860329e7 (first released in 0.54.22-staging; first stable release 0.56.0), which blocks -execdir/-okdir for find.",
  "id": "GHSA-34j2-gcwp-vrv5",
  "modified": "2026-06-17T18:35:56Z",
  "published": "2026-06-17T18:35:56Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-55743"
    },
    {
      "type": "WEB",
      "url": "https://github.com/tinyhumansai/openhuman/commit/60050aa09a870f53ed7e4cd40ed41fd2860329e7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/tinyhumansai/openhuman"
    },
    {
      "type": "WEB",
      "url": "https://github.com/tinyhumansai/openhuman/blob/v0.53.49-staging/src/openhuman/security/policy.rs"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.

Action not permitted

CVE-2026-55743 (GCVE-0-2026-55743)

FKIE_CVE-2026-55743

GHSA-34J2-GCWP-VRV5

Tags

Sightings

Nomenclature