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.

Severity
HIGH
CVSS v3
8.8
CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H · source cna
Exploit chance (EPSS)
2.135%
chance of exploitation in the next 30 days
higher than 82.3% of scored CVEs · 2026-11-17
CISA KEV
Not listed
Public exploit code
Yes
Exploit references (NVD and CNA): 1
Metasploit modules: 0
Nuclei templates: 0

Weakness

CISA SSVC decision points

Exploitationnone
Automatableno
Technical impacttotal
Scored2024-05-16

Timeline

  1. 2024-05-16Published by the CNA09:03 UTC
  2. 2024-05-16GitHub advisory published (GHSA-pw38-xv9x-h8ch)same day
  3. 2024-05-16CISA SSVC decision recordedsame day

The timeline shows what already happened. To be told when this CVE changes next, watch it from the API.

Exploit and advisory records

GitHub advisory GHSA-pw38-xv9x-h8ch, affected packages:

PackageVulnerable versionsFixed in
PyPI llama-indexbefore 0.10.130.10.13
PyPI llama-index-llms-rungptbefore 0.1.30.1.3

Affected products

Products listed as vulnerable. Upgrade to the version under "Fixed in", or a later one.

ProductVulnerable versionsFixed in
llamaindex llamaindexfrom 0.9.47 before 0.10.13fixed in 0.10.130.10.13

Products and versions as NVD and the vendor that published the CVE list them.

References

Get more CVE data from the API.

Free without a key or signup. Pro adds monitoring and higher limits: pricing.

Sources