{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-105755","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","state":"PUBLISHED","assignerShortName":"GitHub_M","dateReserved":"2026-10-05T19:11:07.947Z","datePublished":"2026-10-05T22:47:54.854Z","dateUpdated":"2026-10-06T17:55:21.295Z"},"containers":{"cna":{"title":"vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`","problemTypes":[{"descriptions":[{"cweId":"CWE-639","lang":"en","description":"CWE-639: Authorization Bypass Through User-Controlled Key","type":"CWE"}]}],"metrics":[{"cvssV3_1":{"attackComplexity":"HIGH","attackVector":"NETWORK","availabilityImpact":"LOW","baseScore":4.2,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"LOW","privilegesRequired":"LOW","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L","version":"3.1"}}],"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px"},{"name":"https://github.com/vllm-project/vllm/pull/51445","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/51445"},{"name":"https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc"},{"name":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/releases/tag/v0.30.0"}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":"< 030.0","status":"affected"}]}],"providerMetadata":{"orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M","dateUpdated":"2026-10-05T22:47:54.854Z"},"descriptions":[{"lang":"en","value":"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."}],"source":{"advisory":"GHSA-2phq-3phc-84px","discovery":"UNKNOWN"}},"adp":[{"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-10-06T17:55:11.724369Z","id":"CVE-2026-105755","options":[{"Exploitation":"none"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"title":"CISA ADP Vulnrichment","providerMetadata":{"orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP","dateUpdated":"2026-10-06T17:55:21.295Z"}}]}}