Browse / Improper Output Handling / CVE-2025-9141
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- vllm (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
How it works, in short
The Qwen3-Coder tool-call parser calls eval() on tool parameters of unrecognised type, so model-generated arguments containing Python code run on the server. (Our summary, written by a model. The source text is below.)
Details
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:
1. Tool calling is enabled (--enable-auto-tool-choice)
2. The qwen3_coder parser is specified (--tool-call-parser qwen3_coder)
3. The parameter type is not explicitly defined or recognized
Impact
Remote Code Execution via Python's eval() function.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw
- https://github.com/vllm-project/vllm/pull/21396
- https://github.com/vllm-project/vllm/commit/4594fc3b281713bd3d7634405b4a1393af40d294
- https://github.com/vllm-project/vllm
Source: GitHub Advisory Database, used under CC BY 4.0.