Advisory

PYSEC-2026-2014

Also known as: CVE-2025-9141, GHSA-79j6-g2m3-jgfw

Summary

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

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.

Severity

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

Dates

Published
2026-07-07 16:03 UTC
Modified
2026-07-07 17:47 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.10.0, fixed 0.10.1.1 (ecosystem)

Fixed versions

0.10.1.1

Fix

  • Fixed version 0.10.1.1
    pip install --upgrade vllm==0.10.1.1

Fix 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

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences