alterlab-proteinmpnn

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run python and python to execute standard bioinformatics scripts (parse_multiple_chains.py, protein_mpnn_run.py) from the well-known dauparas/ProteinMPNN repository. These are legitimate operations for the skill's stated purpose of protein sequence design.
  • [EXTERNAL_DOWNLOADS]: The skill mentions cloning the dauparas/ProteinMPNN repository from GitHub. This is a standard practice for using this specific academic tool and is documented neutrally.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, data exfiltration, or persistence mechanisms were detected. The skill primarily serves as a wrapper for academic research tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 11:25 PM
Security Audit — agent-trust-hub — alterlab-proteinmpnn