Vulnerability Information
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
System logs spoofable in Auto-GPT via ANSI control sequences
Vulnerability Description
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. The Auto-GPT command line UI makes heavy use of color-coded print statements to signify different types of system messages to the user, including messages that are crucial for the user to review and control which commands should be executed. Before v0.4.3, it was possible for a malicious external resource (such as a website browsed by Auto-GPT) to cause misleading messages to be printed to the console by getting the LLM to regurgitate JSON encoded ANSI escape sequences (`\u001b[`). These escape sequences were JSON decoded and printed to the console as part of the model's "thinking process". The issue has been patched in release version 0.4.3.
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:L/A:N
Vulnerability Type
日志输出的转义处理不恰当
Vulnerability Title
Auto-GPT 安全漏洞
Vulnerability Description
Auto-GPT是Significant Gravitas开源的一个人工智能软件代理程序。 Auto-GPT 0.4.3之前版本存在安全漏洞，该漏洞源于恶意外部资源可能会通过让 LLM 反省 JSON 编码的 ANSI 转义序列 ( ) 来导致将误导性消息打印到控制台。
CVSS Information
N/A
Vulnerability Type
N/A