improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of purely textual guidelines and pedagogical instructions designed to assist an AI in software architecture reviews.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading and analyzing external documentation (e.g.,
CONTEXT.md,docs/adr/). While this introduces a surface for indirect prompt injection from malicious project files, the risk is negligible as the skill does not execute the content or perform actions beyond generating text-based recommendations. - [NO_CODE]: No shell scripts, Python files, or JavaScript files are distributed with the skill; all logic is contained within the prompt instructions.
Audit Metadata