{"schema_version":"1.9.0","id":"PYSEC-2026-4185","published":"2026-09-26T14:16:47.810Z","modified":"2026-10-07T10:00:03.378975746Z","aliases":["CVE-2026-100652","GHSA-qff2-492f-9fm4"],"details":"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":[{"package":{"name":"vllm","ecosystem":"PyPI","purl":"pkg:pypi/vllm"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.22.0"},{"fixed":"0.24.0"}]}],"versions":["0.22.0","0.22.1","0.23.0"],"ecosystem_specific":{},"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4185.yaml"}}],"references":[{"type":"ADVISORY","url":"https://www.vulncheck.com/advisories/vllm-0.22.0-through-0.23.0-denial-of-service-via-stop-token-ids"},{"type":"EVIDENCE","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-qff2-492f-9fm4"}],"severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H"}]}