seo-schema
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external, untrusted data to perform its primary function.
- Ingestion points: The skill performs "Detection" by scanning page source for JSON-LD, Microdata, and RDFa, and identifies page types from "content analysis" (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed content are provided.
- Capability inventory: The agent has the capability to generate structured files, specifically
SCHEMA-REPORT.mdandgenerated-schema.json(SKILL.md). - Sanitization: There are no instructions for sanitizing or escaping the data extracted from the page source before it is interpolated into the output reports.
Audit Metadata