The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted e-commerce data from external Shopify store APIs which acts as a potential surface for malicious instructions embedded in product descriptions or customer records.\n
Ingestion points: scripts/shopify_client.py retrieves data from Shopify Admin API endpoints including orders, products, and customers.\n
Boundary markers: The agent context does not include explicit delimiters or instructions to treat data returned from the API as untrusted content.\n
Capability inventory: The skill provides capabilities to write analysis files (restricted to the working directory) and perform network operations via Python scripts.\n
Sanitization: The scripts do not perform sanitization or validation of the text data retrieved from the Shopify API before processing or display.\n- [COMMAND_EXECUTION]: The skill provides utility scripts (scripts/analyze.py and scripts/shopify_client.py) intended to be executed by the agent to perform data retrieval and performance auditing.\n- [DATA_EXFILTRATION]: The skill performs network operations to the Shopify Admin API to fetch store information and order history from external store domains.\n- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to clone its repository from GitHub during the installation process.

shopify