Gen Agent Trust Hub

This skill is designed to run Hugging Face model evaluations on local hardware using well-known frameworks like inspect-ai and lighteval. It includes standard Python scripts that facilitate these evaluations. While the scripts utilize shell command execution for core functionality and support loading remote model code—a common requirement in ML development—these activities are consistent with the skill's purpose and are implemented using established tools.

The provider classified the analyzed snapshot as NONE risk. This result applies to the content available at audit time.