Staging Environment: Content and features may be unstable or change without notice.
Advisory details: pypa / vllm/PYSEC-2026-2014
Advisory ID pypa/vllm/PYSEC-2026-2014
Aliases CVE-2025-9141
GHSA-79j6-g2m3-jgfw
PYSEC-2026-2014
Summary 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.
Status Published
Exploitability 0.5
Weighted Severity 7.9
Risk 4.0
Affected and Fixed Packages Package Details
Introduced and Fixed Package Commit Patches Package Commit Patches Details
Weaknesses (0)
There are no known CWE.
No exploits are available.

No EPSS data available for this advisory.

Patch URL
There are no known patches.
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H Found at https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-2014.yaml
Attack Vector (AV) Attack Complexity (AC) Privileges Required (PR) User Interaction (UI) Scope (S) Confidentiality Impact (C) Integrity Impact (I) Availability Impact (A)

network

adjacent_network

local

physical

low

high

none

low

high

none

required

unchanged

changed

high

low

none

high

low

none

high

low

none

There are no SSVC decisions available.