HuggingFace Model Download

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill facilitates downloads from HuggingFace, which is a trusted external source. It utilizes the official 'huggingface_hub' package, which is maintained by a trusted organization.
  • [COMMAND_EXECUTION] (SAFE): The commands provided use 'uv run' to execute the HuggingFace CLI tools. This is a recommended practice for secure and reproducible tool execution without requiring global installations.
  • [CREDENTIALS_UNSAFE] (SAFE): While the skill mentions the 'HF_TOKEN' environment variable, it does so to explain how the official tool handles authentication for gated models. No credentials are hardcoded or exfiltrated.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:47 PM