site-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a set of instructional guidelines and templates for information architecture tasks. It does not include executable scripts, shell commands, or network operations.- [DATA_EXPOSURE]: The skill is designed to read local project files such as .agents/product-marketing.md to gather business context. This behavior is consistent with the intended use case of providing personalized architectural advice based on existing project documentation.- [INDIRECT_PROMPT_INJECTION]: The skill has a defined surface for indirect prompt injection as it ingests data from local marketing context files. However, the risk is negligible as the skill's outputs are limited to text-based planning, ASCII trees, and Mermaid diagrams, with no access to sensitive system APIs or external communication tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 07:44 AM