CVE-2024-4181

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.

Weakness classification

• CWE-94: Improper Control of Generation of Code ('Code Injection')

Primary references

• security@huntr.dev — Patch
• security@huntr.dev — Exploit, Third Party Advisory
• af854a3a-2127-422b-91ae-364da2661108 — Patch
• af854a3a-2127-422b-91ae-364da2661108 — Exploit, Third Party Advisory