CVE DATABASE / CVE-2024-4181
CVE-2024-4181
Summary
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 3.0 breakdown
| Base score | 8.8 (HIGH) |
| Vector | CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| Attack vector | NETWORK |
| Attack complexity | LOW |
| Privileges required | NONE |
| User interaction | REQUIRED |
| Scope | UNCHANGED |
| Confidentiality | HIGH |
| Integrity | HIGH |
| Availability | HIGH |
Weakness type (CWE)
Affected products
Use our free CVE Lookup tool for the latest NVD record, or browse the full CISA KEV catalog.
References
- https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba
- https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1
Data: NIST NVD. NVD last modified 2025-10-21. Always verify against the vendor advisory before acting.