The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the official @membranehq/cli package from the NPM registry. This is a recognized vendor resource used to provide the necessary tooling for the integration.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to manage connections and run actions. These commands are standard operations for the platform and do not involve arbitrary command execution.
[PROMPT_INJECTION]: The skill processes data from Rewardful, which constitutes an indirect prompt injection surface.
Ingestion points: Rewardful entity data (affiliates, customers, subscriptions) entered into the agent context through the output of membrane action run commands.
Boundary markers: No specific delimiters or safety instructions are used in the prompt to separate external data from system instructions.
Capability inventory: The agent has the ability to execute membrane CLI commands for action and connection management.
Sanitization: The skill relies on the structured nature of the JSON output provided by the Membrane platform without additional sanitization logic defined in the prompts.

rewardful