All reports
High

RunGptLLM class in LlamaIndex has a command injection

Affected versions

Version ranges need review.

Affected versions
<0.1.3
Fixed version
0.1.3
Affected versions
< 0.1.3
Fixed version
0.1.3
Affected versions
< 0.10.13
Fixed version
0.10.13
Affected versions
>=0.9.47 <0.10.13
Fixed version
0.10.13

Exploitation

CVE-2024-4181

Probability of exploitation in the next 30 days: 2.14%

FIRST EPSS · 2026-11-20

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.

Links