CVE-2024-4181

8.8HIGH

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

发布于: 5/16/2024更新于: 10/21/2025
在NVD查看在MITRE查看

描述

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.

AI分析AI驱动

受影响产品

llamaindexllamaindex

参考资料