schema
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard instructional content and templates for implementing structured data according to industry best practices. It correctly directs users to official validation tools and documentation from trusted sources like Google.
- [INDIRECT_PROMPT_INJECTION]: The skill includes logic to read project-specific context from local files such as
.agents/product-marketing.md. This represents a data ingestion surface, but it is limited to the intended primary purpose of generating relevant schema markup and does not involve high-risk capabilities. 1. Ingestion points: Local workspace files including.agents/product-marketing.mdand.claude/product-marketing.md. 2. Boundary markers: The instructions do not specify any delimiters or safety warnings for the content read from these files. 3. Capability inventory: The skill's functionality is restricted to text and JSON-LD code block generation; no dangerous capabilities such as network access, file writing, or shell execution are utilized. 4. Sanitization: The skill does not perform explicit sanitization or filtering of the content retrieved from marketing context files.
Audit Metadata