{"id":"CVE-2026-100647","aliases":["GHSA-wpww-v874-ph2p"],"url":"https://o3.security/vulnerability/CVE-2026-100647","summary":"vLLM before 0.29.0 CPU Exhaustion via unbounded cache_salt","details":"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.","published":"2026-09-26T13:23:18.240Z","modified":"2026-09-30T03:30:32.764417661Z","cvss":null,"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[],"fix":null,"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/100xxx/CVE-2026-100647.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-wpww-v874-ph2p"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-100647"},{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-cpu-exhaustion-via-unbounded-cache-salt"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-09-30T03:30:32.764417661Z"}}