The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch live documentation from external sources and perform web searches to retrieve implementation details. This creates a surface where the agent might process untrusted content.
Ingestion points: Instructions in SKILL.md to fetch documentation from docs.bigcommerce.com and use WebSearch for API references.
Boundary markers: The instructions do not specify delimiters or warnings to ignore embedded instructions within the fetched data.
Capability inventory: The skill utilizes tools such as Bash, Write, and Edit, which could be targeted by instructions found in external content.
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from external searches or documentation fetches.
[EXTERNAL_DOWNLOADS]: The skill references and installs official packages and resources from BigCommerce.
Evidence: The skill includes instructions to install @bigcommerce/checkout-sdk via npm and references the bigcommerce/checkout-js repository on GitHub for custom checkout implementations. These are established resources from a well-known service provider.

bc-checkout