seo-schema
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML data to detect and validate JSON-LD blocks, creating a surface for indirect prompt injection.
- Ingestion points: External HTML content identified in the 'Detect existing JSON-LD blocks' step of the workflow in
SKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the ingested HTML.
- Capability inventory: The skill utilizes a local script (
scripts/validate-schema.ts) to process and validate data. - Sanitization: There is no evidence of sanitization, escaping, or validation of the external HTML content before it is passed to the validation script.
- [COMMAND_EXECUTION]: The workflow involves the execution of a project-local TypeScript script (
scripts/validate-schema.ts) to validate schema data against offline dumps.
Audit Metadata