The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions.
Ingestion points: Tools such as SHOPIFY_GET_PRODUCTS, SHOPIFY_GET_ORDERS_WITH_FILTERS, and SHOPIFY_GET_ALL_CUSTOMERS ingest data from a Shopify store (product titles, order notes, customer details) into the agent's context.
Boundary markers: The instructions do not define specific boundary markers or delimiters to isolate untrusted data, nor do they include warnings for the agent to ignore instructions embedded within the Shopify data.
Capability inventory: The skill provides extensive capabilities including product creation (SHOPIFY_BULK_CREATE_PRODUCTS), collection management (SHOPIFY_ADD_PRODUCT_TO_COLLECTION), and arbitrary GraphQL execution (SHOPIFY_GRAPH_QL_QUERY).
Sanitization: No sanitization or validation logic is described for content retrieved from Shopify before it is used to drive subsequent automated actions.

shopify-automation