CVE-2024-4181

published 16 May 2024 · updated 1 Aug 2024

Command Injection in run-llama/llama_index

8.8HighCVSS 8.8EPSS 2%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 2%. Fixed in 0.10.13.

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

Vendors, products and packages with version ranges

VendorProductVersionsFixed
run-llama<0.10.130.10.13

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2024-4181 severity on Zeptric[![CVE-2024-4181](https://zeptric.io/badge/cve/CVE-2024-4181.svg)](https://zeptric.io/cve/CVE-2024-4181)