The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli package from the NPM registry, which is a verified tool from the skill's author to manage the integration.
[COMMAND_EXECUTION]: Provides instructions to execute shell commands using the membrane CLI for logging in, establishing connections, and running payment-related actions.
[SAFE]: Authentication is handled through a managed OAuth-style flow (membrane login), which eliminates the need for the skill to store or access hardcoded credentials or environment secrets.
[PROMPT_INJECTION]: The skill processes external data from the Tomato Pay API, which is an indirect injection surface.
Ingestion points: Data enters the context through the output of the membrane action run command.
Boundary markers: There are no explicit delimiters defined in the instructions to isolate external data.
Capability inventory: The agent has the ability to run shell commands via the CLI to manage and execute API actions.
Sanitization: No explicit sanitization or validation steps for external data are described in the skill markdown.

tomato-pay