The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry. This is the official command-line interface provided by the vendor to manage service integrations.
[COMMAND_EXECUTION]: The agent is instructed to execute various shell commands using the membrane CLI (e.g., membrane login, membrane connect, membrane action run). These commands are necessary for authenticating with the platform and performing data operations.
[PROMPT_INJECTION]: The skill processes data retrieved from the Maxxton API, which constitutes an indirect prompt injection surface.
Ingestion points: External data returned from Maxxton records via the membrane action run command.
Boundary markers: None provided; the agent processes external data within its standard context.
Capability inventory: The agent can execute shell commands through the CLI and interact with the Membrane platform's action creation and execution APIs.
Sanitization: The instructions do not specify any sanitization or validation of the data retrieved from the external API before it is presented to the agent.

maxxton