skills/muco-rolle/skills/write-prd/Gen Agent Trust Hub

write-prd

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements robust data leakage prevention by explicitly forbidding the inclusion of file paths, function names, or code snippets in the final document. This prevents sensitive implementation details from being exposed in external GitHub issues.
  • [PROMPT_INJECTION]: The skill analyzes the local codebase (SKILL.md, Step 2) to inform the PRD. This creates a surface for indirect prompt injection where malicious files could attempt to influence the agent's behavior. However, the risk is mitigated by a human-in-the-loop interview process and the fact that the agent's output is constrained by a predefined template (TEMPLATE.md).
  • [DATA_EXFILTRATION]: The skill facilitates submitting the PRD to GitHub. This network operation targets a whitelisted service for its primary intended purpose. Because the process is human-driven and strictly filters technical identifiers, it does not pose a risk of unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 12:40 PM