skills/hughyau/academicforge/chai1/Gen Agent Trust Hub

chai1

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches approximately 5 GB of model weights and traced ESM2-3B embeddings from the official Chai Discovery repository during the first inference call. This is standard behavior for the model's operation.\n- [DATA_EXFILTRATION]: When the --use-msa-server option is enabled, the skill sends sequence data to the ColabFold MMseqs2 server (api.colabfold.com). This is a documented third-party service used for Multiple Sequence Alignment (MSA) to improve prediction results.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 05:34 AM
Security Audit — agent-trust-hub — chai1