shopify-automation

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure a remote MCP server at https://rube.app/mcp. This endpoint is used to provide the Shopify tool schemas and execution capabilities required for the skill's workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Shopify stores, including orders, customer profiles, and product details. This ingestion of untrusted external content represents a surface for indirect prompt injection attacks.
  • Ingestion points: Tools such as SHOPIFY_GET_ORDERS_WITH_FILTERS, SHOPIFY_GET_ALL_CUSTOMERS, and SHOPIFY_GET_PRODUCT retrieve data from the store environment.
  • Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the retrieved Shopify data.
  • Capability inventory: The skill possesses capabilities to modify the store environment, including SHOPIFY_BULK_CREATE_PRODUCTS, SHOPIFY_ADD_PRODUCT_TO_COLLECTION, and SHOPIFY_CREATE_SMART_COLLECTIONS.
  • Sanitization: No explicit sanitization or validation steps for external data are provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:47 PM