漏洞信息
尽管我们使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。神龙努力确保数据的准确性,但请您根据实际情况进行核实和判断。
Vulnerability Title
LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
Vulnerability Description
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_code=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no publicly available patches.
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Vulnerability Title
lmdeploy 代码注入漏洞
Vulnerability Description
lmdeploy是InternLM开源的一个用于压缩、部署和服务 LLM 的工具包。 lmdeploy 0.12.3及之前版本存在代码注入漏洞,该漏洞源于在多个HuggingFace模型加载点硬编码trust_remote_code=True,可能导致任意代码执行。
CVSS Information
N/A
Vulnerability Type
N/A