site-architecture

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured guidelines for information architecture, including URL patterns and navigation design. It does not perform any sensitive operations or use external tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided business details and read project-specific context files. 1. Ingestion points: Instructions mention reading .agents/product-marketing-context.md and user inputs. 2. Boundary markers: None present. 3. Capability inventory: None. The skill produces text and diagrams only, with no tool access or shell execution. 4. Sanitization: None required as no external commands or tools are invoked.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — site-architecture