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
FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection
Vulnerability Description
A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Vulnerability Title
MetaGPT 代码注入漏洞
Vulnerability Description
MetaGPT是MetaGPT公司的一个多代理框架。 MetaGPT 0.8.1及之前版本存在代码注入漏洞,该漏洞源于对HumanEvalBenchmark/MBPPBenchmark组件中check_solution函数的操作,可能导致代码注入攻击。
CVSS Information
N/A
Vulnerability Type
N/A