The Agent Skills Directory

[SAFE]: The skill is designed for read-only auditing of Shopify store redirects using the official Shopify Admin API. It does not perform any mutations or unauthorized data transfers.
[PROMPT_INJECTION]: The skill processes external data (redirect paths and targets) from the Shopify store. This represents a potential surface for indirect prompt injection, however, the skill's capabilities are limited to local CSV file creation and reporting.
Ingestion points: Shopify urlRedirects GraphQL query in SKILL.md.
Boundary markers: No explicit delimiters or warnings for embedded instructions are present in the processing flow.
Capability inventory: Local file writing (CSV) and GraphQL read-only queries.
Sanitization: The skill does not specify sanitization or escaping of the ingested redirect data.
[COMMAND_EXECUTION]: The prerequisites include a manual step for the user to authenticate via the Shopify CLI (shopify store auth), which is a standard and safe administrative procedure.

url-redirect-audit