CVEvulnerability
CVE-2026-105755
4.2 MEDIUM
Official page ↗
- Status
- Analyzed
- Published
- 2026-10-05
- Last modified
- 2026-10-08
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 4.2 MEDIUM — CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L
- Weaknesses
- CWE-639
Description
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.
Affected configurations
• vllm vllm (< 0.30.0)
Related
Weakness · CWE (1)
- CWE-639 Authorization Bypass Through User-Controlled Key weakness
References
- https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc Patch
- https://github.com/vllm-project/vllm/pull/51445 Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px Vendor Advisory