CriticalCVE
Unpatched Critical LMCache Flaw Lets Unauthenticated Attackers Run Code Remotely
The Hacker News·Source published ·1 min read
What happened?
A critical vulnerability in LMCache, open-source software that speeds up large language model (LLM) servers such as vLLM, lets an attacker run code on the cache server without logging in, and no fixed version is available. The flaw is in LMCache's multiprocess mode, where the cache runs as a standalone server that LLM workers reach over the ZeroMQ messaging library. A single network
Key details
- Server only becomes remotely reachable when configured to listen on a routable address instead of localhost.
- Official Kubernetes deployment example starts server on all interfaces, making it exposed by default.
- Process runs as root in official container images, giving attackers full system privileges.
Affected
- LMCache versions 0.3.9 through 0.5.5, 0.5.6 release candidates, and development branch.
Summarised by SecOraLens from The Hacker News. Always read the original source before acting. How SecOraLens verifies advisories.