seo-schema
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and does not include any executable scripts, shell commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted external data (web page source code). While this creates an attack surface for indirect prompt injection, it is necessary for the skill's intended SEO purpose.
- Ingestion points: Scanning page source for JSON-LD, Microdata, and RDFa as defined in
SKILL.md. - Boundary markers: None identified; the instructions do not specify delimiters for external content.
- Capability inventory: The agent writes analysis results to
SCHEMA-REPORT.mdandgenerated-schema.json. - Sanitization: No specific sanitization or escaping mechanisms for the ingested structured data are mentioned in the instructions.
Audit Metadata