equivariant-architecture-designer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references several scientific libraries (e3nn, escnn, pytorch_geometric, etc.) as recommendations for the user. It does not attempt to download or install them automatically.
  • [COMMAND_EXECUTION] (SAFE): No shell commands or subprocess calls are present in the provided files. All instructions are aimed at guiding the AI's response to the user.
  • [DATA_EXFILTRATION] (SAFE): No network operations, file system access to sensitive paths, or credential markers were detected.
  • [PROMPT_INJECTION] (SAFE): No instructions attempting to bypass safety filters or override system prompts were found. The language is professional and technical.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM