The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally via npm. As this tool is provided by the skill's author (membrane) to facilitate platform access, this is a standard operational dependency.
[COMMAND_EXECUTION]: The skill executes multiple shell commands using the membrane CLI to manage connections, discover actions, and run integration logic. This includes commands like membrane login, membrane connection list, and membrane action run.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external data from the Smaily platform.
Ingestion points: Data retrieved through the output of membrane action run (e.g., email campaign content, contact lists) is fed back into the agent context.
Boundary markers: No specific delimiters or warnings to ignore instructions within the retrieved data are defined in the instructions.
Capability inventory: The agent has the ability to execute shell commands via the Membrane CLI, write to the filesystem, and perform network requests.
Sanitization: There is no explicit sanitization or validation logic provided for the data returned from the API calls.

smaily