CVE-2026-93840 (GCVE-0-2026-93840)
Vulnerability from cvelistv5
Published
2026-09-18 19:06
Modified
2026-09-24 14:23
Severity ?
6.3 (Medium) - CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
3.7 (Low) - CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N
CWE
  • CWE-129 - Improper Validation of Array Index
Summary
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
References
Impacted products
Vendor Product Version
vllm-project vllm Version: 0   ≤
Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-93840",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-21T18:29:51.620755Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-21T18:30:02.425Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/vllm",
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "lessThan": "0.29.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            },
            {
              "status": "unaffected",
              "version": "0.29.0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "0.29.0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Mingkai Yu"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiapeng Li"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiajia Liu"
        }
      ],
      "datePublic": "2026-07-19T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 6.3,
            "baseSeverity": "MEDIUM",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "LOW"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 3.7,
            "baseSeverity": "LOW",
            "confidentialityImpact": "NONE",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-129",
              "description": "Improper Validation of Array Index",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-09-24T14:23:15.056Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "patch",
            "issue-tracking"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/49080"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/vllm-project/vllm"
        },
        {
          "tags": [
            "patch"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191"
        },
        {
          "name": "VulnCheck Advisory: vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-cross-request-logits-corruption-via-allowed-token-ids"
        }
      ],
      "title": "vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-93840",
    "datePublished": "2026-09-18T19:06:06.001Z",
    "dateReserved": "2026-09-18T18:16:47.489Z",
    "dateUpdated": "2026-09-24T14:23:15.056Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-93840\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-21T18:29:51.620755Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-21T18:29:57.171Z\"}}], \"cna\": {\"title\": \"vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids\", \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Mingkai Yu\"}, {\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Jiapeng Li\"}, {\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Jiajia Liu\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 6.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"LOW\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"NONE\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"NONE\"}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 3.7, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"LOW\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"lessThan\": \"0.29.0\", \"versionType\": \"semver\"}, {\"status\": \"unaffected\", \"version\": \"0.29.0\", \"versionType\": \"semver\"}], \"packageURL\": \"pkg:pypi/vllm\", \"defaultStatus\": \"unaffected\"}], \"datePublic\": \"2026-07-19T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/pull/49080\", \"tags\": [\"patch\", \"issue-tracking\"]}, {\"url\": \"https://github.com/vllm-project/vllm\", \"tags\": [\"product\"]}, {\"url\": \"https://github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804\", \"tags\": [\"patch\"]}, {\"url\": \"https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://www.vulncheck.com/advisories/vllm-before-0.29.0-cross-request-logits-corruption-via-allowed-token-ids\", \"name\": \"VulnCheck Advisory: vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-129\", \"description\": \"Improper Validation of Array Index\"}]}], \"cpeApplicability\": [{\"nodes\": [{\"negate\": false, \"cpeMatch\": [{\"criteria\": \"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*\", \"vulnerable\": true, \"versionEndExcluding\": \"0.29.0\"}], \"operator\": \"OR\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-09-24T14:23:15.056Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-93840\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-09-24T14:23:15.056Z\", \"dateReserved\": \"2026-09-18T18:16:47.489Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-09-18T19:06:06.001Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.