Improper input validation in Vllm
CVE-2026-105756
- CVSS v3
- 6.5 Medium
- Public exploits
- None known
- EPSS
- 0.003 · 27.0th percentile
- Published
- 2026-10-05
What to do
- Fixed in
0.30.0- Affected
- 2 affected products
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
- Attack Vector
- Network
AV:N - Attack Complexity
- Low
AC:L - Privileges Required
- Low
PR:L - User Interaction
- None
UI:N - Scope
- Unchanged
S:U - Confidentiality
- None
C:N - Integrity
- None
I:N - Availability
- High
A:H
EPSS exploit prediction
EPSS 0.003, 27.0th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.30.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvj (Mitigation, Vendor Advisory)
- https://github.com/vllm-project/vllm/pull/51444 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174 (Patch)
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 (Release Notes)