site-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed exclusively of Markdown documentation, ASCII templates, and Mermaid diagram examples. It contains no executable scripts, shell commands, or binary files.
- [SAFE]: No network operations, external downloads, or third-party dependencies are defined or utilized within the skill files.
- [SAFE]: The skill instructs the agent to check for project context in specific local files (e.g.,
.agents/product-marketing.md). This is a standard and safe practice for AI agents to retrieve relevant local information without accessing sensitive system or credential files. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting data from external context files without explicit sanitization or boundary markers. However, because the skill's capabilities are limited to generating text-based architectural advice and diagrams, this represents a negligible risk and is consistent with intended agent behavior.
Audit Metadata