schema
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local utility script
scripts/validate_schema.mjsintended to be executed via Node.js to validate schema markup files. This is a functional component of the skill and does not perform network operations or access sensitive system files. - [INDIRECT_PROMPT_INJECTION]: The skill processes JSON-LD structured data which could contain malicious instructions.
- Ingestion points: The
scripts/validate_schema.mjsscript reads user-provided JSON files or stdin. - Boundary markers: The instructions guide the agent to validate specific schema properties but do not explicitly define delimiters for untrusted content.
- Capability inventory: The validation script performs string checking and JSON parsing; it does not contain subprocess execution or network calls.
- Sanitization: The script uses
JSON.parse()to ensure the input is valid JSON, which limits the risk of instruction following. - [EXTERNAL_DOWNLOADS]: The documentation refers to official validation tools and guidelines from Google Search Central and Schema.org. These references are to well-known, trusted industry resources used for legitimate verification purposes.
Audit Metadata