hf-upload

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs its stated purpose of HuggingFace integration using official tools and user-provided credentials. No malicious behavior was detected.
  • [EXTERNAL_DOWNLOADS]: The skill requires the huggingface_hub library, which is a standard dependency from a well-known service provider, to facilitate API interactions.
  • [DATA_EXFILTRATION]: The skill is designed to upload data (learning snapshots, traces) to HuggingFace. This is an intended functionality using the user's own repositories and API keys.
  • [CREDENTIALS_UNSAFE]: HuggingFace tokens are accessed from the environment. The skill correctly implements credential masking in its configuration reporting to prevent full token exposure in logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:59 PM