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
Command Injection in run-llama/llama_index
Vulnerability Description
A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.
CVSS Information
N/A
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Vulnerability Title
LlamaIndex 代码注入漏洞
Vulnerability Description
LlamaIndex是Jerry Liu个人开发者的一个 LLM 应用程序的数据框架。 LlamaIndex 0.9.47版本存在代码注入漏洞,该漏洞源于 eval 函数的不当使用,允许恶意或受损的 LLM 托管提供商在客户端计算机上执行任意命令。
CVSS Information
N/A
Vulnerability Type
N/A