seo-schema
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external URLs to detect and validate structured data, which creates an indirect prompt injection surface.
- Ingestion points: The skill scans HTML page source for JSON-LD, Microdata, and RDFa content (
SKILL.md). - Boundary markers: The instructions lack explicit delimiters or specific 'ignore embedded instructions' warnings for the data being analyzed.
- Capability inventory: The skill has the ability to fetch external URLs and perform file read/write operations within the
.seo-cache/directory. - Sanitization: The skill performs JSON syntax validation and schema compliance checks, but does not explicitly filter the ingested content for natural language instructions.
Audit Metadata