codebase-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational and provides a shared vocabulary for software engineering practices such as 'deep modules', 'interfaces', and 'seams'.
- [EXTERNAL_DOWNLOADS]: The skill includes a link to a GitHub repository (
github.com/mattpocock/skills) as a source citation for the content. This is a reference to a well-known developer's public repository and is considered safe and informational. - [DYNAMIC_EXECUTION]: The 'Design It Twice' pattern mentions spawning 'sub-agents'. In the context of AI agent platforms, this refers to orchestrating multiple model calls to explore design alternatives, not the execution of arbitrary or malicious scripts.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user requests regarding code design, it does not ingest untrusted data in a way that could lead to command execution or data exfiltration. The instructions are focused on architectural review.
Audit Metadata