The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl and jq to interact with the Shopify Admin REST API. While these are standard tools for this purpose, they execute shell commands directly on the host system.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. Malicious content within Shopify data (e.g., product titles, customer notes, or order details) could potentially influence the agent's behavior when processed.
Ingestion points: Data is retrieved via curl from the $SHOPIFY_STORE_URL endpoint.
Boundary markers: No explicit delimiters or warnings are present in the provided bash snippets to isolate data from instructions.
Capability inventory: The skill possesses the capability to execute shell commands (curl, jq) and read/write to the Shopify store.
Sanitization: The skill uses jq to parse and filter JSON fields, which provides some structural sanitization, but doesn't prevent natural language instructions within those fields from being interpreted by the LLM.

shopify