vllm
Affected
- introduced
0.10.0, fixed0.10.1.1(ecosystem)
Fixed versions
0.10.1.1
Fix
- Fixed version
0.10.1.1pip install --upgrade vllm==0.10.1.1
Advisory
Also known as: CVE-2025-9141, GHSA-79j6-g2m3-jgfw
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
Summary
An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call.
Details
vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval() function to parse tool call parameters. This occurs during the parameter conversion process when the parser attempts to handle unknown data types.
This code path is reached when:
--enable-auto-tool-choice)--tool-call-parser qwen3_coder)Impact
Remote Code Execution via Python's eval() function.
High Basis: CVSS v3 score 8.8, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
0.10.0, fixed 0.10.1.1 (ecosystem)0.10.1.1
0.10.1.1pip install --upgrade vllm==0.10.1.1Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0