implementing-schema-markup
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing guidance and JSON-LD templates for search engine optimization tasks. It references well-known validation tools from Google and Schema.org.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for processing website data to generate structured schema markup, which represents a potential surface for indirect prompt injection if the user provides malicious content to be marked up.
- Ingestion points: The skill reads page content, business goals, and current schema implementation details provided by the user, as well as context from
.claude/product-marketing-context.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the source data are provided.
- Capability inventory: The skill is designed to generate text output in the form of JSON-LD code blocks; it does not contain subprocess calls, network exfiltration commands, or file-writing capabilities.
- Sanitization: No explicit sanitization or validation of the user-provided data is mentioned before it is incorporated into the JSON-LD output.
Audit Metadata