CVE-2025-9141 – vllm

Package

Manager: pip
Name: vllm
Vulnerable Version: >=0.10.0 <0.10.1.1

Severity

Level: High

CVSS v3.1: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CVSS v4.0: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

EPSS: N/A pctlN/A

Details

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](https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py) 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.

Metadata

Created: 2025-08-21T14:46:51Z
Modified: 2025-08-21T14:46:51Z
Source: https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2025/08/GHSA-79j6-g2m3-jgfw/GHSA-79j6-g2m3-jgfw.json
CWE IDs: ["CWE-502"]
Alternative ID: GHSA-79j6-g2m3-jgfw
Finding: F096
Auto approve: 1