proteinmpnn-nim

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts exclusively with official NVIDIA API endpoints (health.api.nvidia.com) and the NVIDIA Container Registry (nvcr.io) for scientific computing tasks.
  • [SAFE]: API credentials are managed securely through environment variables (NGC_API_KEY), avoiding hardcoded secrets and following industry standards.
  • [SAFE]: All tool usage, including file processing of PDB structures and Docker management for local inference, is restricted to the skill's documented biological design purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:03 AM
Security Audit — agent-trust-hub — proteinmpnn-nim