The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of a global Node.js package to facilitate communication with the platform.\n
Evidence: npm install -g @membranehq/cli.\n
Context: This is the official CLI tool provided by the vendor (Membrane) to manage service connections.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute various CLI commands to perform operations.\n
Evidence: Commands include membrane login, membrane action run, and membrane request to interact with the Aimtell API via a proxy.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests data from external API responses.\n
Ingestion points: Data returned from list-campaigns, list-subscribers, and other actions are incorporated into the agent's context.\n
Boundary markers: No specific delimiters or "ignore instructions" warnings are applied to the external data output.\n
Capability inventory: The skill includes high-privilege capabilities such as create-campaign, update-website-settings, and delete-campaign.\n
Sanitization: The instructions do not define methods for validating or sanitizing the content retrieved from the Aimtell API.

aimtell