The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the membrane CLI to perform operations such as authentication, action discovery, and running webinar-related tasks. These commands are the intended method for interacting with the vendor's platform.
[EXTERNAL_DOWNLOADS]: The instructions direct the user to install the @membranehq/cli package from npm. This is the official command-line interface provided by the vendor (Membrane) and is required to facilitate the integration.
[PROMPT_INJECTION]: The skill processes data from external API responses (e.g., registrant names, event details) which are returned via CLI commands. While this is a standard integration surface, it represents a potential point for indirect prompt injection if those responses contain instructions intended to influence the agent.
Ingestion points: Output from membrane action list and membrane action run as described in SKILL.md.
Boundary markers: No explicit delimiters are suggested in the example commands for handling remote data.
Capability inventory: The agent can execute system commands through the membrane CLI.
Sanitization: Sanitization of API outputs is not explicitly detailed in the integration instructions.
[CREDENTIALS_UNSAFE]: No hardcoded API keys or secrets are present. The skill correctly utilizes the membrane login and membrane connect workflows, which manage authentication tokens server-side or via local secure storage.

demio