site-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of documentation, templates, and instructions for information architecture planning. It contains no executable scripts, shell commands, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest project-specific information from local context files (e.g.,
.agents/product-marketing-context.md). While this provides a surface for data-driven instruction influence, the lack of high-risk capabilities (such as network access or shell execution) and the inherent requirement for project context in planning tasks render this risk factor minimal and safe in context.
Audit Metadata