The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local source files and external API response headers, which could theoretically contain malicious instructions designed to influence the agent's behavior during migration.
Ingestion points: The skill reads and modifies local .ts, .js, and .toml files using grep and sed. It also processes the x-shopify-api-deprecated-reason header from Shopify API responses.
Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are utilized when reading file content or API header values.
Capability inventory: The skill uses Read, Write, Edit, and Bash (including curl, npm, sed, and grep) capabilities, providing a significant surface for file and network operations.
Sanitization: The instructions do not specify any validation or sanitization for the data retrieved from local files or API response headers before they are logged or used in file modification commands.

shopify-upgrade-migration