schema-markup
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [No Code] (SAFE): The skill consists exclusively of documentation and examples in Markdown; no executable code (Python, Node.js, etc.) is included.
- [Indirect Prompt Injection] (LOW): The skill creates a surface for indirect instructions by processing external files and user data.
- Ingestion points: Reads project context from
.claude/product-marketing-context.mdand processes user-provided site details. - Boundary markers: The instructions do not define delimiters for untrusted user data or context files.
- Capability inventory: Generates structured JSON-LD and Next.js/React code snippets (using
dangerouslySetInnerHTML). - Sanitization: No sanitization logic is provided to handle potentially malicious input within the generated code templates, which could lead to cross-site scripting (XSS) if implemented directly.
Audit Metadata