testing-principles

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill consists entirely of instructional Markdown files and review templates. No executable binary files, scripts, or malicious logic are included in the package.
  • COMMAND_EXECUTION (SAFE): The SKILL.md file contains a 'Validation' section with standard shell commands (bash, find, bunx) for linting documentation links and verifying the skill structure. These are benign utility commands for development maintenance.
  • EXTERNAL_DOWNLOADS (SAFE): The skill mentions 'markdown-link-check' (via bunx), which is a standard, reputable tool for ensuring link integrity in documentation. No unknown or untrusted external dependencies are required.
  • PROMPT_INJECTION (SAFE): The instructional content (MUST/SHOULD/Anti-patterns) provides legitimate behavioral guidelines for an AI agent to perform code reviews and does not attempt to bypass safety filters or override core system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 11:30 PM