fair-esm2

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses torch.hub to download pre-trained model weights from Meta AI's official distribution server (dl.fbaipublicfiles.com). This is standard behavior for the fair-esm package.
  • [COMMAND_EXECUTION]: Provides examples for submitting remote compute jobs using a platform-specific API. The commands shown, such as python3 embed_esm2.py, are routine for executing the described protein embedding tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:21 AM
Security Audit — agent-trust-hub — fair-esm2