NIST deprecates RSA-2048 from 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
HIGH severity

CVE-2025-9141 — vllm

HIGHFix: vllm-project/vllm#21396

CVE-2025-9141 is a high-severity (CVSS 8.8) remote code execution vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

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

Also known asPYSEC-2026-2014
Published
Updated
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 10, 2026 · OSV.dev, FIRST.org (EPSS)

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.10.0&&< 0.10.1.10.10.1.1pip install --upgrade 'vllm==0.10.1.1'

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.10.1.1 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-9141 is resolved across your whole dependency graph.

  3. Workarounds

    Do not deserialise data from untrusted sources: where the format allows it, restrict deserialisation to an explicit allowlist of expected types, and prefer a data-only format (JSON, Protobuf) over one that can reconstruct arbitrary objects until you can upgrade.

Frequently Asked Questions

### 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:
O3 Security · Impact-Aware SCA

Is CVE-2025-9141 in your dependencies?

Find it across PyPI, including transitive dependencies.