bm-prd-creator

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to read various configuration files (e.g., "package.json", "Gemfile", "pyproject.toml") and analyze the project's folder structure to automatically detect the existing technology stack.
  • [COMMAND_EXECUTION]: The agent is directed to create a "_build_plan/" directory and write multiple documentation and milestone files. The instructions specify writing these files directly once the interview phases are complete, bypassing a final draft review in favor of the iterative approvals obtained during the interview.
  • [EXTERNAL_DOWNLOADS]: The generated "prd.html" template includes links to external assets from well-known services, including Tailwind CSS, Google Fonts, and Lucide icons, for the purpose of styling the visual documentation.
  • [COMMAND_EXECUTION]: The skill modifies the project's agent instruction files ("CLAUDE.md" or "AGENTS.md") by appending a section that explains the purpose and temporary nature of the "_build_plan/" directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 06:11 PM
Security Audit — agent-trust-hub — bm-prd-creator