漏洞信息
神龙判断
是否为 Web 类漏洞： 未知
判断理由：
N/A
提示
尽管我们采用了先进的大模型技术，但其输出仍可能包含不准确或过时的信息。
神龙会尽力确保数据准确，但也请结合实际情况进行甄别与判断。
神龙祝您一切顺利！
漏洞标题
vLLM affected by RCE via auto_map dynamic module loading during model initialization
漏洞描述信息
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
CVSS信息
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
漏洞类别
对生成代码的控制不恰当(代码注入)