site-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from local context files such as .agents/product-marketing-context.md if they exist.
  • Ingestion points: .agents/product-marketing-context.md or .claude/product-marketing-context.md (referenced in SKILL.md).
  • Boundary markers: None explicitly defined to delimit the content of the marketing context file.
  • Capability inventory: None. The skill does not perform subprocess calls, file writes, or network operations, nor does it request access to restricted tools.
  • Sanitization: No sanitization is performed on the ingested content, but the lack of executable capabilities makes this surface benign.
  • [SAFE]: The skill is purely informational, consisting of markdown guidelines, ASCII templates, and Mermaid diagram examples for information architecture. No malicious patterns or behaviors were detected across the provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 04:54 PM
Security Audit — agent-trust-hub — site-architecture