schema-markup
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from a local context file and user inputs to generate JSON-LD schema blocks. \n
- Ingestion points:
.claude/product-marketing-context.mdand user-provided site details. \n - Boundary markers: Absent; the skill does not use delimiters to isolate the ingested context file content from the system instructions. \n
- Capability inventory: The skill generates JSON-LD code intended for deployment on the user's website. \n
- Sanitization: Absent; the skill relies on the LLM's default behavior when interpolating project context into code templates. \n- [Data Exposure] (SAFE): The skill accesses a specific project context file (
.claude/product-marketing-context.md) which is standard for maintaining consistency and does not target sensitive user credentials or system files. \n- [External Downloads] (SAFE): Referenced URLs for testing and validation are for reputable, trusted domains (search.google.com and validator.schema.org).
Audit Metadata