CVE-2026-105756
vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
CVSS Score
6.5
EPSS Score
0.0%
EPSS Percentile
0th
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.
| CWE | CWE-20 CWE-248 |
| Vendor | vllm-project |
| Product | vllm |
| Published | Oct 5, 2026 |
Stay Ahead of the Next One
Get instant alerts for vllm-project vllm
Be the first to know when new medium vulnerabilities affecting vllm-project vllm are published — delivered to Slack, Telegram or Discord.
Get Free Alerts →
Free · No credit card · 60 sec setup
CVSS v3 Breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High
Affected Versions
vllm-project / vllm
< 0.30.0
References
github.com: https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvj github.com: https://github.com/vllm-project/vllm/pull/51444 github.com: https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174 github.com: https://github.com/vllm-project/vllm/releases/tag/v0.30.0