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
PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()
Vulnerability Description
PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval() in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM interception of API requests, or a malicious custom LLM endpoint to execute arbitrary code in Zotero's chrome-privileged context, enabling file read/write, process execution, and access to all Zotero data.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/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
PapersGPT 代码注入漏洞
Vulnerability Description
PapersGPT是papersgpt个人开发者的一款人工智能软件工具。 PapersGPT 0.6.1版本存在代码注入漏洞,该漏洞源于views.ts中LLM端点返回的恶意代码未经清理即传递给window.eval(),可能导致攻击者通过PDF提示注入、中间人拦截API请求或恶意自定义LLM端点,在Zotero的chrome特权上下文中执行任意代码,实现文件读写、进程执行及访问所有Zotero数据。
CVSS Information
N/A
Vulnerability Type
N/A