The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry. This is the primary tool used for the integration and originates from the platform's official distribution channel.
[COMMAND_EXECUTION]: The skill relies on shell commands to interact with the Membrane CLI for logging in, connecting to services, and running actions. These operations are essential to the skill's primary function and are performed using the vendor's own tooling.
[CREDENTIALS_UNSAFE]: The skill demonstrates good security posture by explicitly instructing the agent never to ask for API keys or tokens. Instead, it uses a connection-based OAuth flow where credentials are managed server-side by the Membrane platform.
[INDIRECT_PROMPT_INJECTION]: The skill includes functionality to run actions that accept JSON parameters. While this presents an ingestion point for external data, the risk is standard for integration skills and is mitigated by the use of structured input schemas.

clio-manage