schema
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external context from local files and user-supplied site data to generate structured markup.
- Ingestion points: Reads context from files like
.agents/product-marketing.mdand processes user-provided product/FAQ text inSKILL.md. - Boundary markers: The instructions do not use specific delimiters for user input, but the output is restricted to structured JSON-LD format.
- Capability inventory: Generates JSON-LD blocks for articles, products, and local businesses; does not execute code or perform network requests.
- Sanitization: Proactively provides security guidance in
references/schema-examples.mdfor Next.js implementations, recommending the use of.replace(/</g, '\\u003c')to prevent script termination and cross-site scripting (XSS) when embedding serialized JSON in HTML. - [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or unauthorized command execution were detected. All external links point to trusted documentation or validation services (Google and Schema.org).
Audit Metadata