CVE-2024-4181: Llamaindex

High severity, CVSS 8.8. EPSS: 2.1% chance of exploitation in the next 30 days.

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.

Affected products

• Llamaindex Llamaindex: from 0.9.47, before 0.10.13 (fixed in 0.10.13)

Published 2024-05-16. Last modified 2026-06-17.