seo-schema
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill presents an indirect prompt injection surface by scanning external web content. Ingestion points: SKILL.md scans page source for JSON-LD, Microdata, and RDFa. Boundary markers: Absent; there are no instructions to ignore embedded commands. Capability inventory: SKILL.md allows generating files and reports. Sanitization: Absent; the skill validates schema structure but not instruction content.
Audit Metadata