The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs agents to clone the Saleor core repository from GitHub (https://github.com/saleor/saleor.git) into the /tmp directory to investigate internal API behavior. This targets the official repository belonging to the skill's authoring organization.
[COMMAND_EXECUTION]: Provides shell command examples using git clone and grep to help agents navigate and understand the Saleor source code and permission resolvers.
[INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting data from an external GraphQL API, which represents a surface for indirect prompt injection if the API content is untrusted.
Ingestion points: API response fields such as product.description and product.attributes as described in rules/api-data-model.md and AGENTS.md.
Boundary markers: The skill does not define specific delimiters for separating API data from instructions.
Capability inventory: The skill suggests using file system and investigation tools like git and grep as noted in rules/api-investigation.md.
Sanitization: Instructions focus on API logic and type safety; specific sanitization for preventing injection via API data fields is not provided.
[NO_CODE]: The skill package consists entirely of Markdown files providing instructions and references; it does not contain any executable scripts or binary files.

saleor-storefront