skills/companion-inc/feynman/diffdock/Gen Agent Trust Hub

diffdock

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists entirely of high-level instructions for planning and performing molecular docking tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processing scientific data files such as PDB, mmCIF, SDF, and SMILES formats. While it has no built-in execution capabilities, it describes an ingestion surface for external data.
  • Ingestion points: Input protein structures and ligand files defined in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: No subprocess calls, code execution, or network operations are present in the skill.
  • Sanitization: No explicit sanitization or validation of molecular file content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:04 AM
Security Audit — agent-trust-hub — diffdock