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
Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing
Vulnerability Description
Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0.
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Vulnerability Type
动态执行代码中指令转义处理不恰当(Eval注入)
Vulnerability Title
Xorbits Inference 代码注入漏洞
Vulnerability Description
Xorbits Inference是Xorbits团队开源的一个功能强大且用途广泛的库,专为语言、语音识别和多模态模型而设计。 Xorbits Inference 2.5.0及之前版本存在代码注入漏洞,该漏洞源于在xinference/model/llm/tool_parsers/llama3_tool_parser.py和xinference/model/llm/utils.py中,将攻击者影响的Llama3工具调用输出传递给eval()函数求值,可能导致未经身份验证的远程攻击者通过特制提示词在服务器进
CVSS Information
N/A
Vulnerability Type
N/A