~ / search / GHSA-pw38-xv9x-h8ch

GHSA-pw38-xv9x-h8ch

RunGptLLM class in LlamaIndex has a command injection

Source: GitHub Advisory Database (reviewed) High CVE-2024-4181

Packages

EcosystemPackageAffectedFixed in
PyPI llama-index < 0.10.13 0.10.13
PyPI llama-index-llms-rungpt < 0.1.3 0.1.3

Details

As written in the advisory (Markdown source, shown as plain text).

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

External links from the advisory. They lead to third-party sites.