CVE-2025-66448
中文标题:
（暂无数据）
英文标题:
vLLM vulnerable to remote code execution via transformers_utils/get_config
漏洞描述
中文描述:
（暂无数据）
英文描述:
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.
CWE类型:
标签:
受影响产品
| 厂商 | 产品 | 版本 | 版本范围 | 平台 | CPE |
|---|---|---|---|---|---|
| vllm-project | vllm | < 0.11.1 | - | - |
cpe:2.3:a:vllm-project:vllm:<_0.11.1:*:*:*:*:*:*:*
|
| vllm | vllm | * | - | - |
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
|
解决方案
中文解决方案:
英文解决方案:
临时解决方案:
参考链接
CVSS评分详情
3.1 (cna)
HIGHCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
时间信息
利用信息
数据源详情
| 数据源 | 记录ID | 版本 | 提取时间 |
|---|---|---|---|
| CVE | cve_CVE-2025-66448 |
2025-12-03 03:24:29 | 2026-01-12 02:12:24 |
| NVD | nvd_CVE-2025-66448 |
2025-12-04 03:00:02 | 2026-01-12 02:28:04 |
版本与语言
安全公告
变更历史
查看详细变更
- affected_products_count: 1 -> 2
- data_sources: ['cve'] -> ['cve', 'nvd']