The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the @membranehq/cli tool from the official npm registry. This is a vendor-owned resource used for interfacing with the Membrane platform.
[COMMAND_EXECUTION]: Utilizes the membrane command-line tool to handle login procedures, manage connection lifecycles, and execute requests against the Pushpay API.
[PROMPT_INJECTION]: As an integration that retrieves external data (donations, member records, and form entries), the skill has an indirect prompt injection surface.
Ingestion points: API response data is ingested through the membrane action run and membrane request commands.
Boundary markers: No explicit delimiters are specified in the instructions to separate untrusted data from agent instructions.
Capability inventory: The skill can perform shell commands via the membrane CLI and make network requests through the Membrane proxy.
Sanitization: The skill relies on the agent's internal safety filters and the structured nature of the JSON responses for data safety.

pushpay