schema-markup
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingests external content (page types, existing schema) and user-provided goals to generate markup. This represents a standard input-output surface for a coding assistant. While it lacks explicit sanitization instructions for the generated JSON-LD, the risk is minimal as the agent's primary capability is text generation rather than side-effect actions.\n- [Data Exposure] (INFO): The skill attempts to read
.claude/product-marketing-context.md. This is a standard practice for context-aware agents and does not constitute unauthorized data access.
Audit Metadata