medium4.2
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`
Impact
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 packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | < 0.30.0 | 0.30.0 |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Vllm | Vllm | before 0.30.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/advisories/GHSA-2phq-3phc-84px
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px
- https://github.com/vllm-project/vllm/pull/51445
- https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0