skills/edwinhu/workflows/dev-design/Gen Agent Trust Hub

dev-design

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run python3 to execute local guard scripts (phase-gate-guard.py and dev-plan-executable-guard.py) located within the plugin root. These are used as internal validation hooks to ensure documentation standards are met.
  • [COMMAND_EXECUTION]: Instructs the agent to invoke Skill(skill="workflows:dev-worktree") to create isolated git worktrees. This is a standard development workflow and operates within the local repository context.
  • [SAFE]: The skill's architecture enforces a 'Iron Law of Design', preventing the AI from performing implementation tasks without explicit user confirmation via the AskUserQuestion tool.
  • [SAFE]: No hardcoded credentials, sensitive file access, or non-whitelisted external network operations were detected in the instructions or templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:29 AM
Security Audit — agent-trust-hub — dev-design