← Back
2026-09-26 13:23CVE-2026-100652VulnCheck
PUBLISHED5.2CWE-20

vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

Problem type

Affected products

vllm-project

vllm

< 0.24.0 - AFFECTED

0.24.0 - UNAFFECTED

References

GitHub Security Advisory (GHSA-qff2-492f-9fm4)

https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4

vendor-advisory
VulnCheck Advisory: vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids

third-party-advisory

GitHub Security Advisories

GHSA-gxcm-7c4h-f56c

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in...

https://github.com/advisories/GHSA-gxcm-7c4h-f56c

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

github.com

https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4

nvd.nist.gov

https://nvd.nist.gov/vuln/detail/CVE-2026-100652

vulncheck.com

https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids

github.com

https://github.com/advisories/GHSA-gxcm-7c4h-f56c

JSON source

https://cveawg.mitre.org/api/cve/CVE-2026-100652
Click to expand
{
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "cveMetadata": {
    "cveId": "CVE-2026-100652",
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "dateUpdated": "2026-09-26T13:23:21.865Z",
    "dateReserved": "2026-09-26T02:33:07.899Z",
    "datePublished": "2026-09-26T13:23:21.865Z",
    "state": "PUBLISHED"
  },
  "containers": {
    "cna": {
      "providerMetadata": {
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck",
        "dateUpdated": "2026-09-26T13:23:21.865Z"
      },
      "datePublic": "2026-09-12T00:00:00.000Z",
      "title": "vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids",
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart."
        }
      ],
      "affected": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "defaultStatus": "unaffected",
          "versions": [
            {
              "version": "0.22.0",
              "status": "affected",
              "versionType": "semver",
              "lessThan": "0.24.0"
            },
            {
              "version": "0.24.0",
              "status": "unaffected",
              "versionType": "semver"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "lang": "en",
              "description": "Improper Input Validation",
              "cweId": "CWE-20",
              "type": "CWE"
            }
          ]
        }
      ],
      "references": [
        {
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4",
          "name": "GitHub Security Advisory (GHSA-qff2-492f-9fm4)",
          "tags": [
            "vendor-advisory"
          ]
        },
        {
          "url": "https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids",
          "name": "VulnCheck Advisory: vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids",
          "tags": [
            "third-party-advisory"
          ]
        }
      ],
      "metrics": [
        {
          "format": "CVSS"
        },
        {
          "format": "CVSS",
          "cvssV3_1": {
            "version": "3.1",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H",
            "attackVector": "NETWORK",
            "attackComplexity": "HIGH",
            "privilegesRequired": "NONE",
            "userInteraction": "NONE",
            "scope": "UNCHANGED",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "availabilityImpact": "HIGH",
            "baseScore": 5.9,
            "baseSeverity": "MEDIUM"
          }
        }
      ],
      "credits": [
        {
          "lang": "en",
          "value": "rexpository",
          "type": "reporter"
        },
        {
          "lang": "en",
          "value": "jperezdealgaba",
          "type": "coordinator"
        }
      ]
    }
  }
}