site-architecture
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and reference documents follow established information architecture principles. There are no patterns of prompt injection, data exfiltration, or malicious command execution.
- [SAFE]: The skill uses local context gathering (e.g., reading
.agents/product-marketing.md) which is a standard practice for personalizing agent output without external exposure. - [SAFE]: All output formats (ASCII trees, Mermaid diagrams, and URL maps) are static text representations and do not involve dynamic code execution or runtime compilation.
Audit Metadata