HomeLlamaindexCVE-2024-4181

CVE-2024-4181

HIGH
8.8CVSS
Published: 2024-05-16
Updated: 2025-10-21
AI Analysis

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 Metrics

Vector
CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector
network
Complexity
low
Privileges
none
User Action
required
Scope
unchanged
Confidentiality
high
Integrity
high
Availability
high
Weaknesses
CWE-94

Metadata

Primary Vendor
LLAMAINDEX
Published
5/16/2024
Last Modified
10/21/2025
Source
NIST NVD
Note: Verify all details with official vendor sources before applying patches.

Affected Products

llamaindex : llamaindex

AI-Powered Remediation

Generate remediation guidance or a C-suite brief for this vulnerability.

Executive Intelligence Brief

CVE-CVE-2024-4181 | HIGH Severity | CVEDatabase.com | CVEDatabase.com