seo-schema
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external content, creating a surface for indirect prompt injection.\n
- Ingestion points: Website source code (JSON-LD, Microdata, RDFa) fetched via
WebFetchbased on user-provided URLs.\n - Boundary markers: Absent. There are no instructions to the agent to disregard instructions potentially embedded within the data retrieved from external URLs.\n
- Capability inventory: The skill is authorized to use
Bash,Write,Read,Grep,Glob, andWebFetchtools.\n - Sanitization: None described. The skill parses the raw content to identify and validate schema types without explicit sanitization steps for the data being analyzed.
Audit Metadata