huggingface-hub

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading machine learning models and datasets from Hugging Face (huggingface.co). Hugging Face is a well-known and widely used platform for machine learning assets. The skill uses official tools like huggingface-cli and the huggingface_hub Python library to perform these operations.
  • [COMMAND_EXECUTION]: The skill includes shell commands for package installation (pip install), cache management, and repository interaction. These commands are standard for machine learning development workflows and do not exhibit suspicious behavior.
  • [CREDENTIALS_UNSAFE]: While the skill mentions authentication and the HF_TOKEN environment variable, it correctly uses placeholders (e.g., hf_...) and refers users to official settings pages to obtain their own tokens, adhering to standard security practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 05:23 PM
Security Audit — agent-trust-hub — huggingface-hub