{"id":"PYSEC-2026-4198","details":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.","aliases":["CVE-2026-105755","GHSA-2phq-3phc-84px"],"modified":"2026-10-08T10:00:02.862032490Z","published":"2026-10-05T23:17:02.167Z","references":[{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/51445"}],"affected":[{"package":{"name":"vllm","ecosystem":"PyPI","purl":"pkg:pypi/vllm"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.30.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.24.0","0.25.0","0.25.1","0.26.0","0.27.0","0.27.1","0.28.0","0.29.0","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"ecosystem_specific":{},"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4198.yaml"}}],"schema_version":"1.9.0","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L"}]}