schema
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read external context files such as
.agents/product-marketing.mdor.claude/product-marketing.mdto inform its responses. - Ingestion points: The agent context is extended by reading local markdown files containing product and marketing information.
- Boundary markers: The skill lacks explicit instructions to treat the content of these context files as untrusted data or to ignore any embedded instructions within them.
- Capability inventory: The skill primarily generates JSON-LD structured data and provides SEO advice. It does not perform shell executions, network requests, or file writes.
- Sanitization: There is no explicit mention of sanitizing or validating the data retrieved from context files before interpolation into schema templates.
Audit Metadata