codebase-design
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely educational and instructional, defining a shared vocabulary and design methodology for codebase architecture.
- [SAFE]: No executable scripts, binary files, or external network requests are present. The skill operates entirely within the agent's reasoning and dialogue context.
- [SAFE]: The mentioned 'sub-agents' in DESIGN-IT-TWICE.md are a prompting pattern for the LLM to explore multiple perspectives, not a mechanism for executing untrusted code or privilege escalation.
- [SAFE]: The skill uses standard markdown and YAML frontmatter without any obfuscation, hidden URLs, or prompt injection attempts.
Audit Metadata