The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm. This package is an official resource provided by the vendor (Membrane) for platform integration and is considered a safe dependency.- [COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to interact with the Mailerlite API. These commands are part of the intended functionality and handle authentication securely through the vendor's infrastructure.- [PROMPT_INJECTION]: The skill facilitates processing data from the Mailerlite API, creating a surface for potential indirect prompt injection. This is a common characteristic of data integration skills and not a specific security flaw in the instructions themselves. Ingestion points: Data from Mailerlite API responses via membrane action run and membrane request. Boundary markers: None identified in the current instructions. Capability inventory: The agent can execute shell commands via the membrane CLI. Sanitization: No explicit sanitization of external API content is documented in the skill instructions.

mailerlite