| Component | vLLM |
| Severity | medium (CVSS 4.2) |
| CVSS vector | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L |
| Published (NVD) | 2026-10-05 |
| Last modified | 2026-10-08 |
| Affected versions | vllm < 0.30.0 |
| Fixed in | 0.30.0 |
| Weakness | CWE-639 |
| CISA KEV | not listed |
NVD 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.
What to do
- Upgrade vLLM to
0.30.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-105755
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2phq-3phc-84px
- 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
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cach...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...