prd

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses dynamic context injection (!git branch, !git log, !git status) solely for grounding the agent in the current repository state. These commands are non-malicious and standard for development-oriented agents.
  • [SAFE]: The skill includes a mandatory 'Skip-condition check' that prevents it from running on engineering-internal tasks like refactors, infrastructure changes, or bug fixes, ensuring it remains within its intended business-driven scope.
  • [SAFE]: All file operations are restricted to writing documentation (PRD.md) within the project's contract or memory slices (defaulting to docs/topics/). It does not attempt to modify source code, configuration files, or sensitive system directories.
  • [SAFE]: The skill does not perform external network operations or download untrusted code. It relies on locally provided templates and existing conversation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — prd