The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official NPM registry. This is a standard procedure for using the vendor's tooling and does not pose a security risk.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations like logging in, connecting to services, and running actions. These commands are part of the intended functionality for interacting with the Brevo API via the Membrane platform.
[DATA_EXFILTRATION]: The skill explicitly advises against asking users for secrets or API keys, recommending instead the use of Membrane's managed connection system. This is a positive security practice that prevents sensitive credential exposure within the agent environment.
[DYNAMIC_EXECUTION]: The membrane action create command allows the platform to generate new integration logic based on a natural language description. This process occurs on the vendor's platform and is a documented feature of the service.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Brevo CRM (e.g., contacts, deals). While this involves ingesting external data, the risk is mitigated by the use of structured JSON output and the specialized nature of the CRM integration.

brevo