The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides tools for the agent to ingest potentially untrusted data from the Shopify Admin API (e.g., product descriptions, order notes, or customer names).
Ingestion points: Data fetched via scripts/shopify_graphql.py through methods like get_products, get_orders, and get_customers.
Boundary markers: The provided templates do not include specific delimiters or instructions to the LLM to ignore potential instructions embedded within the fetched data.
Capability inventory: The skill allows for local file writing and directory creation (scripts/shopify_init.py), network operations (scripts/shopify_graphql.py), and local CLI execution (scripts/shopify_init.py).
Sanitization: The utility script does not implement sanitization or validation of the content returned by the Shopify API before it is processed by the agent.
[COMMAND_EXECUTION]: The initialization script contains a command execution to check the local environment status.
Evidence: scripts/shopify_init.py utilizes subprocess.run(['shopify', 'version']). This is a benign implementation used to verify that the official Shopify CLI is installed and accessible, posing no risk of command injection.
[EXTERNAL_DOWNLOADS]: The skill instructions and documentation recommend the installation of official developer tools.
Evidence: README.md and SKILL.md direct the user to install @shopify/cli from the official npm registry. These references target a well-known service and are necessary for the skill's primary functionality.

shopify-development