schema
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read and incorporate context from external files such as
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md. If these files are controlled by an attacker or contain untrusted third-party information, they could host malicious instructions designed to influence the agent's behavior during the schema generation process. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It ingests untrusted data from project files (Ingestion point:
.agents/product-marketing.md) and uses this data to generate JSON-LD markup. While it provides validation checklists, it lacks explicit boundary markers or instructions to ignore embedded commands within the ingested marketing context (Sanitization: absent). This could lead to the agent following instructions hidden in the data rather than generating valid schema.
Audit Metadata