CVE-2025-9141
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:
- Tool calling is enabled (
--enable-auto-tool-choice) - The qwen3_coder parser is specified (
--tool-call-parser qwen3_coder) - The parameter type is not explicitly defined or recognized
Impact
Remote Code Execution via Python's eval() function.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
What each source reports
GitHub Advisories Score usedGHSA-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:
- Tool calling is enabled (
--enable-auto-tool-choice) - The qwen3_coder parser is specified (
--tool-call-parser qwen3_coder) - The parameter type is not explicitly defined or recognized
Impact
Remote Code Execution via Python's eval() function.
- Record
GHSA-79j6-g2m3-jgfw- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-502
- Updated
- 2026-11-02
OSVGHSA-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:
- Tool calling is enabled (
--enable-auto-tool-choice) - The qwen3_coder parser is specified (
--tool-call-parser qwen3_coder) - The parameter type is not explicitly defined or recognized
Impact
Remote Code Execution via Python's eval() function.
- Record
GHSA-79j6-g2m3-jgfw- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-502
- Updated
- 2026-11-02
OSVPYSEC-2026-2014
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:
- Tool calling is enabled (
--enable-auto-tool-choice) - The qwen3_coder parser is specified (
--tool-call-parser qwen3_coder) - The parameter type is not explicitly defined or recognized
Impact
Remote Code Execution via Python's eval() function.
- Record
PYSEC-2026-2014- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-02
Affected packages
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | GitHub Advisories, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2025-9141 is a high vulnerability (CVSS 8.8) in vllm, published August 21, 2025. No source lists public exploit code. Fixed in vllm 0.10.1.1.
References
github.com/vllm-project/vllm/security/advisories/GHSA-79j6-g2m3-jgfw
pypi.org/project/vllm
nvd.nist.gov/vuln/detail/CVE-2025-9141