schema
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to read project-specific context files such as
.agents/product-marketing.mdto inform its responses. This creates a surface where malicious instructions embedded in these files could influence agent behavior. - Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when reading these files.
- Capability inventory: The skill generates JSON-LD code blocks and provides technical implementation guidance.
- Sanitization: The Next.js implementation example provided in
references/schema-examples.mdusesdangerouslySetInnerHTMLwithJSON.stringify(schema). This pattern lacks escaping for HTML tags (e.g.,<), which is a security best practice for JSON-LD to prevent potential XSS if the data source is untrusted.
Audit Metadata