The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's functionality is limited to analyzing content and generating structured data templates.
[INDIRECT_PROMPT_INJECTION]: The skill processes page content to determine schema eligibility, creating an ingestion surface for potentially untrusted data.
Ingestion points: Local file content accessed via the Read tool.
Boundary markers: None explicitly defined to isolate source content from the agent's internal instructions.
Capability inventory: The skill is restricted to Read, Glob, and Grep tools; it lacks network access, file-writing capabilities, or shell execution.
Sanitization: Instructions emphasize strict adherence to official documentation and technical JSON-LD validation, which limits the impact of adversarial content within the source data.

schema-markup