site-architecture

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions and reference templates for website information architecture. No executable code or suspicious commands were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read local configuration files for business context (e.g., .agents/product-marketing.md). While this is a data ingestion point, the skill's outputs are limited to text, tables, and Mermaid diagrams, presenting no significant risk of exploitation through this vector.
  • [EXTERNAL_DOWNLOADS]: The skill references external URLs for schema documentation (schema.org) and a marketing skills registry on GitHub. These are used as informational references and do not involve remote code execution or automated downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 02:38 PM