subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a logical workflow for task delegation, utilizing specialized prompts for different roles (implementer, spec reviewer, and code quality reviewer).
  • [SAFE]: All external references (such as superpowers:using-git-worktrees) refer to internal skills within the same developer ecosystem, representing standard modular design.
  • [SAFE]: The skepticism instructed in the spec-reviewer-prompt.md ("Do Not Trust the Report") is a functional reliability measure intended to ensure the reviewer verifies the actual code changes rather than relying on an AI-generated summary. This does not constitute a malicious prompt injection or an attempt to bypass safety filters.
  • [SAFE]: No signs of obfuscation, hardcoded credentials, or unauthorized network operations were found in the skill or its associated templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:35 PM
Security Audit — agent-trust-hub — subagent-driven-development