seo-schema
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external web pages (JSON-LD, Microdata, RDFa) to detect and validate SEO schema. It lacks explicit boundary markers to delimit this external content from agent instructions, creating a surface for indirect prompt injection where a malicious website could embed instructions to manipulate the agent's output or actions.
- Ingestion points:
SKILL.mdinstructions for scanning page source (HTML, JSON-LD, Microdata, RDFa). - Boundary markers: The instructions do not define delimiters or provide 'ignore' rules for external content.
- Capability inventory: The skill writes analysis results to
SCHEMA-REPORT.mdandgenerated-schema.json. - Sanitization: The skill performs structural schema validation but lacks security sanitization to prevent the interpretation of data as instructions.
Audit Metadata