seo-schema-structured-data
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes the
extract_schematool to retrieve and process structured data from external URLs, creating an indirect prompt injection surface where instructions hidden within external web content could be ingested into the agent's context.\n - Ingestion points: Content is ingested from external URLs via the
extract_schematool referenced in README.md and SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters or directives to ignore instructions embedded in the extracted content.\n
- Capability inventory: The skill enables the agent to analyze external data and generate JSON-LD markup.\n
- Sanitization: No sanitization or escaping of content retrieved from external sources is specified.\n- [EXTERNAL_DOWNLOADS]: The skill references official and well-known validation tools for structured data verification.\n
- Evidence: Links to Google's Rich Results Test and the Schema.org Validator are provided in the documentation.
Audit Metadata