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 todocs/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