The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions specify using the curl utility to perform HTTP requests (GET, POST, PATCH, DELETE) and the jq utility to parse JSON responses. This is a standard method for API interaction within a shell environment.
[PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing external data from the Buttondown API without explicit sanitization or boundary instructions.
Ingestion points: Data is ingested through API responses from endpoints such as /subscribers, /emails, and /tags in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for processing external content.
Capability inventory: The skill has the capability to perform network requests and command execution via curl and jq as defined in SKILL.md.
Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from the API before use.

buttondown