site-architecture
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional content and reference templates for information architecture. No executable code or scripts are included in the package.
- [DATA_EXFILTRATION]: The skill instructions include reading local project files (e.g., '.agents/product-marketing.md') to gather business context. This is a standard practice for context-aware agents and does not involve accessing sensitive system credentials or transmitting data to external domains.
- [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection by ingesting data from external marketing context files. However, the risk is minimal as the skill lacks capabilities to execute commands or perform network operations.
- Ingestion points: Reads '.agents/product-marketing.md', '.claude/product-marketing.md', and 'product-marketing-context.md' as specified in 'SKILL.md'.
- Boundary markers: None identified; instructions direct the agent to read and use the content directly.
- Capability inventory: No subprocess calls, file writes, or network tools are requested or used.
- Sanitization: No validation or sanitization is performed on the ingested marketing context.
Audit Metadata