The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill instructions are purely informational, focusing on information architecture best practices. The skill uses standard Mermaid diagrams and ASCII trees for visualization, which pose no security risk.- [SAFE]: Data ingestion is limited to reading project-specific context files (e.g., .agents/product-marketing.md), which is expected behavior for providing context-aware architectural advice and does not target sensitive system credentials or configurations.- [SAFE]: No evidence of prompt injection, obfuscation, or remote code execution was found across all provided markdown and reference files. The skill does not install third-party packages or perform network operations.

site-architecture