physicalai-train-adding-a-policy

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is a technical guide for developers, providing instructions for code organization, class inheritance, and local testing. It does not contain any instructions to bypass safety filters or exfiltrate data.
  • [COMMAND_EXECUTION]: The workflow includes local execution of development and testing tools such as uv run, pytest, physicalai fit, and prek run. These are standard tools within the project's context for verifying code integrity and running training steps locally.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 01:43 PM
Security Audit — agent-trust-hub — physicalai-train-adding-a-policy