Vulnerability-Lookup

CVE-2026-73558 (GCVE-0-2026-73558)

Vulnerability from cvelistv5 – Published: 2026-08-13 15:06 – Updated: 2026-08-13 15:38

Title

vLLM: Cross-User Data Leak Vulnerability

Summary

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.

Severity

5.3 (Medium)


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

SSVC

Exploitation: poc Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-13 15:38 UTC

CWE

CWE-190 - Integer Overflow or Wraparound

Assigner

GitHub_M mitre root

References

5 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/issues/42860	x_refsource_MISC
https://github.com/vllm-project/vllm/pull/49660	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/45122…	x_refsource_MISC
https://github.com/vllm-project/vllm/releases/tag…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
vllm-project	vllm	Affected: < 0.27.0	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-73558",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-13T15:38:18.767062Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-13T15:38:40.181Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.27.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user\u0027s input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user\u0027s inference result. This issue is fixed in version 0.27.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-190",
              "description": "CWE-190: Integer Overflow or Wraparound",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-13T15:06:06.584Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
        },
        {
          "name": "https://github.com/vllm-project/vllm/issues/42860",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/issues/42860"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/49660",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/49660"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
        }
      ],
      "source": {
        "advisory": "GHSA-7m6h-x95x-82q5",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM: Cross-User Data Leak Vulnerability"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-73558",
    "datePublished": "2026-08-13T15:06:06.584Z",
    "dateReserved": "2026-08-12T20:53:46.380Z",
    "dateUpdated": "2026-08-13T15:38:40.181Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-73558",
      "date": "2026-09-22",
      "epss": "0.00326",
      "percentile": "0.25919"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "vllm",
                "vendor": "vllm-project",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.27.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user\u0027s input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user\u0027s inference result. This issue is fixed in version 0.27.0."
          }
        ],
        "id": "CVE-2026-73558",
        "lastModified": "2026-09-09T20:58:37.713",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 1.6,
              "impactScore": 3.6,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-73558",
                "options": [
                  {
                    "exploitation": "poc"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-13T15:38:18.767062Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-08-13T15:20:18.220",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/vllm-project/vllm/issues/42860"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/vllm-project/vllm/pull/49660"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
          },
          {
            "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Awaiting Analysis",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-190"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Moderate",
      "current_release_date": "2026-08-19T17:41:27+00:00",
      "cve": "CVE-2026-73558",
      "id": "CVE-2026-73558",
      "initial_release_date": "2026-08-13T15:06:06.584000+00:00",
      "product_status:known_affected": "26",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "vllm: vLLM: Cross-User Data Leakage via Integer Overflow",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-73558.json",
      "version": "3"
    },
    "suse_vex": {
      "aggregate_severity": "moderate",
      "current_release_date": "2026-08-14T17:12:53Z",
      "cve": "CVE-2026-73558",
      "id": "CVE-2026-73558",
      "initial_release_date": "2026-08-14T17:12:53Z",
      "source": "SUSE CSAF VEX",
      "status": "interim",
      "title": "SUSE CVE CVE-2026-73558",
      "url": "https://ftp.suse.com/pub/projects/security/csaf-vex/cve-2026-73558.json",
      "version": "2"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-73558",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-13T15:38:18.767062Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-13T15:38:33.352Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.27.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user\u0027s input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user\u0027s inference result. This issue is fixed in version 0.27.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 5.3,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-190",
                  "description": "CWE-190: Integer Overflow or Wraparound",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-13T15:06:06.584Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
            },
            {
              "name": "https://github.com/vllm-project/vllm/issues/42860",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/issues/42860"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/49660",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/49660"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
            },
            {
              "name": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
            }
          ],
          "source": {
            "advisory": "GHSA-7m6h-x95x-82q5",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM: Cross-User Data Leak Vulnerability"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-73558",
        "datePublished": "2026-08-13T15:06:06.584Z",
        "dateReserved": "2026-08-12T20:53:46.380Z",
        "dateUpdated": "2026-08-13T15:38:40.181Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-73558

Vulnerability from fkie_nvd - Published: 2026-08-13 15:20 - Updated: 2026-09-09 20:58

Severity

5.3 (Medium) - CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924
	security-advisories@github.com	https://github.com/vllm-project/vllm/issues/42860
	security-advisories@github.com	https://github.com/vllm-project/vllm/pull/49660
	security-advisories@github.com	https://github.com/vllm-project/vllm/releases/tag/v0.27.0
	security-advisories@github.com	https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.27.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user\u0027s input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user\u0027s inference result. This issue is fixed in version 0.27.0."
    }
  ],
  "id": "CVE-2026-73558",
  "lastModified": "2026-09-09T20:58:37.713",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 5.3,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 1.6,
        "impactScore": 3.6,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-73558",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-08-13T15:38:18.767062Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-08-13T15:20:18.220",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/vllm-project/vllm/issues/42860"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/vllm-project/vllm/pull/49660"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Awaiting Analysis",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-190"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-7M6H-X95X-82Q5

Vulnerability from github – Published: 2026-09-08 20:24 – Updated: 2026-09-08 20:24

Summary

vLLM: Cross-User Data Leak Vulnerability

Details

Summary

An integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user's inference result, resulting in cross-user data leakage.

Details

The root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82.

As a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A's output to contain portions of User B's inference result. In some cases, User B's response may be copied entirely into User A's response.

This constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.

PoC

We reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.

Using the following configuration:

Batch size: 17 Sequence length: 16384

The final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.

Impact

This vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim's request and cause the victim's inference output to be copied into the attacker's response.

As a result, sensitive information contained in another user's model response may be exposed to an unauthorized party.

Versions

For versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.

Severity

5.3 (Medium)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.27.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-73558"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-190"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-08T20:24:49Z",
    "nvd_published_at": "2026-08-13T15:20:18Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\nAn integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user\u0027s inference result, resulting in cross-user data leakage.\n\n\n### Details\nThe root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82. \n\nAs a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A\u0027s output to contain portions of User B\u0027s inference result. In some cases, User B\u0027s response may be copied entirely into User A\u0027s response.\n\nThis constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.\n### PoC\nWe reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.\n\nUsing the following configuration:\n\nBatch size: 17\nSequence length: 16384\n\nThe final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.\n\n### Impact\nThis vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim\u0027s request and cause the victim\u0027s inference output to be copied into the attacker\u0027s response.\n\nAs a result, sensitive information contained in another user\u0027s model response may be exposed to an unauthorized party.\n\n### Versions\n\nFor versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.",
  "id": "GHSA-7m6h-x95x-82q5",
  "modified": "2026-09-08T20:24:49Z",
  "published": "2026-09-08T20:24:49Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-73558"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/issues/42860"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/49660"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Cross-User Data Leak Vulnerability"
}

PYSEC-2026-3935

Vulnerability from pysec - Published: 2026-09-10 09:45 - Updated: 2026-09-10 11:02

Details

Summary

Details

The root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82.

This constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.

PoC

We reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.

Using the following configuration:

Batch size: 17 Sequence length: 16384

The final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.

Impact

As a result, sensitive information contained in another user's model response may be exposed to an unauthorized party.

Versions

For versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.

Severity

5.3 (Medium)


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

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.27.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.11.0",
        "0.11.1",
        "0.11.2",
        "0.12.0",
        "0.13.0",
        "0.14.0",
        "0.14.1",
        "0.15.0",
        "0.15.1",
        "0.16.0",
        "0.17.0",
        "0.17.1",
        "0.18.0",
        "0.18.1",
        "0.19.0",
        "0.19.1",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.20.0",
        "0.20.1",
        "0.20.2",
        "0.21.0",
        "0.22.0",
        "0.22.1",
        "0.23.0",
        "0.24.0",
        "0.25.0",
        "0.25.1",
        "0.26.0",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-73558",
    "GHSA-7m6h-x95x-82q5"
  ],
  "details": "### Summary\nAn integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user\u0027s inference result, resulting in cross-user data leakage.\n\n\n### Details\nThe root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82. \n\nAs a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A\u0027s output to contain portions of User B\u0027s inference result. In some cases, User B\u0027s response may be copied entirely into User A\u0027s response.\n\nThis constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.\n### PoC\nWe reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.\n\nUsing the following configuration:\n\nBatch size: 17\nSequence length: 16384\n\nThe final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.\n\n### Impact\nThis vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim\u0027s request and cause the victim\u0027s inference output to be copied into the attacker\u0027s response.\n\nAs a result, sensitive information contained in another user\u0027s model response may be exposed to an unauthorized party.\n\n### Versions\n\nFor versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.",
  "id": "PYSEC-2026-3935",
  "modified": "2026-09-10T11:02:35.628775Z",
  "published": "2026-09-10T09:45:00.769969Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-73558"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/issues/42860"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/49660"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-7m6h-x95x-82q5"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Cross-User Data Leak Vulnerability"
}

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.

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.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2026-73558 (GCVE-0-2026-73558)

FKIE_CVE-2026-73558

GHSA-7M6H-X95X-82Q5

Summary

Details

PoC

Impact

Versions

PYSEC-2026-3935

Summary

Details

PoC

Impact

Versions

Tags

Sightings

Nomenclature

Related by attack behaviour