seo-schema
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of instructional Markdown and JSON-LD templates. It contains no executable scripts, shell commands, or binary files, precluding direct remote code execution or persistence attacks.
- [SAFE]: All external URLs link to official developer documentation or the author's public repository. There are no obfuscated URLs or suspicious remote resources included in the skill references.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) as it instructs the agent to scan external web content for schema tags. 1. Ingestion points: Scanning page source for JSON-LD, Microdata, and RDFa tags. 2. Boundary markers: The instructions do not specify delimiters for external content. 3. Capability inventory: The agent's capabilities are limited to generating reports and code snippets. 4. Sanitization: No explicit content filtering or sanitization rules are defined for the ingested data. The potential risk is negligible as the skill lacks dangerous system permissions or network-writing capabilities.
Audit Metadata