CVE-2025-9141
vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
描述
### 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.
如何修補 CVE-2025-9141
要修補 CVE-2025-9141,請將受影響套件升級到下列已修補版本。
- —升級至 0.10.1.1 或更新版本
- —升級至 0.10.1.1 或更新版本
CVE-2025-9141 正在被利用嗎?
目前沒有被利用訊號。CVE-2025-9141 既不在 CISA KEV 也沒有最新的 EPSS 分數。
受影響套件(2)
- >= 0.10.0, < 0.10.1.1
- >= 0.10.0, < 0.10.1.1
CVSS 分數
| 來源 | 版本 | 嚴重程度 | 向量 |
|---|---|---|---|
| osv | CVSS 3.1 | HIGH8.8 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |