AIHacker Newsabout 3 hours ago
LLMs could exploit inference engines to control hosts
1 min read
Malicious LLMs could exploit bugs in inference engines like vLLM or SGLang to execute arbitrary code on host machines. CVE-2025-9141 was an arbitrary-code execution bug in vLLM's XML-based tool parser for Qwen3 Coder, which passed tool-call arguments to eval.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
