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
Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
Vulnerability Description
Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability Type
CWE-1427
Vulnerability Title
Amazon Strands Agents Tools 提示词注入漏洞
Vulnerability Description
Amazon Strands Agents Tools是美国Amazon公司开源的一款人工智能智能体工具。 Amazon Strands Agents Tools 0.8.5之前版本存在提示词注入漏洞,该漏洞源于python_repl工具中用于LLM提示的输入中和不当,可能导致远程攻击者通过特制提示绕过人工同意门,将non_interactive_mode作为关键字参数通过批量工具转发,从而在代理主机上执行任意Python代码。
CVSS Information
N/A
Vulnerability Type
N/A