CVE-2026-105755
mediumvLLM is an inference and serving engine for large language models.
Vendor / product: Vllm — vllm
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.
CVSS
4.2
4.2 (CVSS v3.1)
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L Severity source: NVD CVSS v3.1 (security-advisories@github.com)
Timeline (UTC)
Published: 2026-10-05 23:17
Modified: 2026-10-08 01:28
NVD status: Analyzed
Last synced 3 days ago
Verified against the source API 2026-10-27 06:57 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
vllm / vllm <0.30.0
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
Patch / mitigation: https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc
Patch / mitigation: https://github.com/vllm-project/vllm/pull/51445
References
- https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc security-advisories@github.com
- https://github.com/vllm-project/vllm/pull/51445 security-advisories@github.com
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 security-advisories@github.com
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px security-advisories@github.com
Data sources
NVD CVE API 2.0 — fetched 2026-10-27 06:57 UTC · record ↗