high7.5
CVE-2026-114050
vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes.
Impact
vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes. Unauthenticated attackers can desynchronize the P0/P1 processor caches to trigger a fatal token-placeholder mismatch, killing the entire serving instance until restarted.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | vllm | < 0.31.0 | 0.31.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/advisories/GHSA-p92p-rxj5-7p2x
- https://github.com/vllm-project/vllm/security/advisories/GHSA-p92p-rxj5-7p2x
- https://github.com/vllm-project/vllm/pull/57833
- https://github.com/vllm-project/vllm/commit/7268f6e38ebbb3d61700f16c638c6eba0c88bb0c
- https://github.com/vllm-project/vllm/releases/tag/v0.31.0
- https://nvd.nist.gov/vuln/detail/cve-2026-114050
- https://www.vulncheck.com/advisories/vllm-before-0.31.0-remote-engine-crash-via-forged-multimodal-uuid