shopify
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via data retrieved from the Shopify API.
- Ingestion points: External data such as product titles, descriptions, and customer information is ingested into the agent's context across various scripts, including
products.rb,orders.rb, andcustomers.rb. - Boundary markers: The instructions do not implement boundary markers or specific guidance to ensure the agent ignores potential instructions embedded within the Shopify store data.
- Capability inventory: The skill possesses capabilities for network operations and modifying store data (creating/updating products and customers), which could be leveraged if an indirect injection were successful.
- Sanitization: There is no evidence of content sanitization for data fetched from the API before it is passed to the agent.
Audit Metadata