MEDIUM 4.2 NVD
CVE-2026-105755
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 e
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.
References
- https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc
- https://github.com/vllm-project/vllm/pull/51445
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px
This medium severity vulnerability with a CVSS score of 4.2 was published on 2026-10-05 via NVD.
vulnfeed aggregates 7729 vulnerabilities from NVD, CISA KEV,
Ubuntu, Debian, Red Hat, Kubernetes, Exploit-DB, OSS-Security, GitHub and OpenStack — updated every 4 hours.