site-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide expert guidance on information architecture, URL structuring, and navigation design. All instructions and references are aligned with this purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is instructed to read external marketing context files (e.g.,
.agents/product-marketing.md) if they exist. However, the risk is negligible because the skill lacks the capabilities to perform dangerous actions. - Ingestion points:
SKILL.md(Context gathering section). - Boundary markers: Absent; no specific instructions to disregard embedded malicious content in the external files.
- Capability inventory: None; the skill is limited to generating Markdown text, ASCII trees, and Mermaid diagrams. It does not have access to tools for network communication, file system modification, or command execution.
- Sanitization: Absent; no explicit sanitization for external context is defined.
Audit Metadata