The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches and installs the official Membrane CLI (@membranehq/cli) from the public npm registry to manage integrations and authentication.
[COMMAND_EXECUTION]: Uses the membrane command-line utility to perform operations such as searching for connectors, establishing authenticated connections, and executing API actions.
[PROMPT_INJECTION]: Processes external data from the Plasmic API, which serves as a potential surface for indirect prompt injection. The skill recommends using pre-built actions which helps structure the data received.
Ingestion points: Output data from membrane action run and membrane request commands.
Boundary markers: Absent in the documentation.
Capability inventory: Ability to execute arbitrary shell commands through the membrane CLI.
Sanitization: Relies on the agent to parse and interpret JSON responses from the command line.

plasmic