Executive Summary
An unpatched critical LMCache flaw in multiprocess mode lets unauthenticated attackers run code on the cache server used with LLM servers like vLLM.
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
Affected Products
- LMCache
- vLLM
Vulnerability / Attack Technique
Unauthenticated remote code execution in LLM serving infrastructure
Technical Mechanism
The standalone cache server accepts network messages without authentication.
AI Security Category
LLM03:2025 Supply Chain
Part of the AI Supply Chain and AI SBOM topic.
Relevant Frameworks
RealGround Analysis
LLM serving components are internet-facing infrastructure. RealGround analysis: isolate the cache network until a fix ships.
Recommended Controls
- Restrict LMCache's network exposure to trusted workers only
- Avoid multiprocess mode until patched
Related RealGround Service
AI Agent SBOM and LLM Mapping · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/10/unpatched-critical-lmcache-flaw-lets.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.