site-architecture

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions and formatting templates for site mapping and information architecture.
  • [DATA_EXFILTRATION]: The skill references reading business context from local files such as .agents/product-marketing-context.md. This is a standard operation for specialized agents to gather context and does not involve accessing sensitive system credentials or unauthorized network operations.
  • [PROMPT_INJECTION]: The skill processes user-supplied content inventories and marketing context files. While this creates an indirect prompt injection surface, the skill lacks high-risk capabilities such as command execution or network exfiltration, minimizing the potential impact.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:05 PM
Security Audit — agent-trust-hub — site-architecture