Browse / Improper Output Handling / CVE-2024-4181
RunGptLLM class in LlamaIndex has a command injection
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Affected
- llama-index (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 2.1% chance of exploitation in 30 days
How it works, in short
A malicious or compromised LLM provider's response is passed to eval in RunGptLLM, letting it run commands on the client machine. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-4181
- https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba
- https://github.com/run-llama/llama_index
- https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1
Source: GitHub Advisory Database, used under CC BY 4.0.