What’s Vulnerable › Vulnerabilities

CVE-2026-105755: 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`

• Severity: medium (CVSS 4.2 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-05 · updated 2026-10-08
• Weakness: 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 products

• vllm-project vllm: before 0.30.0 — fixed in 0.30.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.30.0. Check the vendor advisory for mitigations.

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

Get alerted when CVE-2026-105755 or the next vulnerability affects your stack