The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the user to perform authentication via the Shopify CLI (shopify auth login) as a prerequisite. This is a standard procedure for Shopify administrative tools.
[DATA_EXPOSURE]: The skill reads Shopify legal policies (Shipping, Returns, etc.) using GraphQL queries. This data is handled within the context of the Shopify admin environment and used for the stated purpose of auditing readability.
[PROMPT_INJECTION]: There is a potential for indirect prompt injection (Category 8) because the skill processes policy text that is intended for consumption by AI agents. If a policy body were to contain malicious instructions, a downstream agent reading that policy might be affected. However, the skill itself does not facilitate this attack beyond its primary function of reading/writing policy text.
Ingestion points: Policy bodies are read from the Shopify API in Workflow Step 1.
Boundary markers: None specified in the instructions for the data being read.
Capability inventory: The skill possesses the shopPolicyUpdate mutation capability to modify live store content.
Sanitization: No explicit sanitization of policy HTML/text is described before processing.
[EXTERNAL_DOWNLOADS]: No external code or packages are downloaded. The skill relies on locally supplied HTML files if the user chooses to apply updates.

shopify-admin-agentic-policy-readability