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.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
Low
Basic privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
None
No data leak
Integrity
None
No data modification
Availability
High
Complete denial of service
CVSS Vector v3.1
Weakness Type (CWE)
Vulnerable Products
vllm-project:vllm
References 4
https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvj
https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvj
https://github.com/vllm-project/vllm/pull/51444
https://github.com/vllm-project/vllm/pull/51444
https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b…
https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174
https://github.com/vllm-project/vllm/releases/tag/v0.30.0
https://github.com/vllm-project/vllm/releases/tag/v0.30.0