The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's workflow includes ingesting untrusted data from external sources, which creates a vulnerability to indirect prompt injection.
Ingestion points: Data collection methods include "Website scraping" from user-provided URLs and importing data from a "Spreadsheet/CSV file" as noted in SKILL.md.
Boundary markers: There are no instructions for the agent to use delimiters or ignore embedded instructions within the scraped or imported content.
Capability inventory: The skill has high-impact capabilities, including the ability to create, update, and delete store products through GraphQL mutations and shell-based network requests.
Sanitization: The skill lacks explicit sanitization or validation protocols for the external data it processes before passing it to the Shopify API.
[COMMAND_EXECUTION]: The skill explicitly instructs and provides templates for using curl to interact with the Shopify GraphQL Admin API. This involves the execution of shell commands and the management of sensitive authentication tokens within the command environment.

shopify-products