The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally from the npm registry. This is the official tool provided by the vendor for interacting with their platform.
[COMMAND_EXECUTION]: The skill uses various subcommands of the membrane CLI (e.g., login, connect, action run) to manage integrations. These commands are necessary for the skill's stated purpose of automating workflows via the Membrane platform.
[CREDENTIALS_SAFE]: The skill explicitly advises against asking users for API keys or tokens. Instead, it utilizes a server-side connection model where credentials are managed by the platform, reducing the risk of accidental credential exposure in logs or prompts.
[DATA_INGESTION_SURFACE]: The skill processes data from WorkOS via the membrane action run command. While this represents a surface for indirect prompt injection from external data, the risk is mitigated by the use of the vendor's managed infrastructure and standard CLI patterns.
Ingestion points: WorkOS records and event data retrieved via membrane action run.
Boundary markers: Not explicitly defined in the CLI instructions.
Capability inventory: The skill can execute shell commands (membrane CLI) and provision new actions (membrane action create).
Sanitization: Relies on the Membrane platform's internal handling of action logic and output schemas.

workos