← Back
2026-09-26 13:23CVE-2026-100647VulnCheck
PUBLISHED5.2CWE-20

vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.

Problem type

Affected products

vllm-project

vllm

< 0.29.0 - AFFECTED

0.29.0 - UNAFFECTED

References

GitHub Security Advisory (GHSA-wpww-v874-ph2p)

https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p

vendor-advisory
VulnCheck Advisory: vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt

https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt

third-party-advisory

GitHub Security Advisories

GHSA-hm89-h84f-px3x

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter...

https://github.com/advisories/GHSA-hm89-h84f-px3x

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.

github.com

https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p

nvd.nist.gov

https://nvd.nist.gov/vuln/detail/CVE-2026-100647

vulncheck.com

https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt

github.com

https://github.com/advisories/GHSA-hm89-h84f-px3x

JSON source

https://cveawg.mitre.org/api/cve/CVE-2026-100647
Click to expand
{
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "cveMetadata": {
    "cveId": "CVE-2026-100647",
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "dateUpdated": "2026-09-26T13:23:18.240Z",
    "dateReserved": "2026-09-26T02:33:07.898Z",
    "datePublished": "2026-09-26T13:23:18.240Z",
    "state": "PUBLISHED"
  },
  "containers": {
    "cna": {
      "providerMetadata": {
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck",
        "dateUpdated": "2026-09-26T13:23:18.240Z"
      },
      "datePublic": "2026-09-12T00:00:00.000Z",
      "title": "vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt",
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests."
        }
      ],
      "affected": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "defaultStatus": "unaffected",
          "versions": [
            {
              "version": "0",
              "status": "affected",
              "versionType": "semver",
              "lessThan": "0.29.0"
            },
            {
              "version": "0.29.0",
              "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-wpww-v874-ph2p",
          "name": "GitHub Security Advisory (GHSA-wpww-v874-ph2p)",
          "tags": [
            "vendor-advisory"
          ]
        },
        {
          "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt",
          "name": "VulnCheck Advisory: vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt",
          "tags": [
            "third-party-advisory"
          ]
        }
      ],
      "metrics": [
        {
          "format": "CVSS"
        },
        {
          "format": "CVSS",
          "cvssV3_1": {
            "version": "3.1",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L",
            "attackVector": "NETWORK",
            "attackComplexity": "LOW",
            "privilegesRequired": "NONE",
            "userInteraction": "NONE",
            "scope": "UNCHANGED",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "availabilityImpact": "LOW",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM"
          }
        }
      ],
      "credits": [
        {
          "lang": "en",
          "value": "wildoranges",
          "type": "reporter"
        },
        {
          "lang": "en",
          "value": "jperezdealgaba",
          "type": "coordinator"
        }
      ]
    }
  }
}