The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the membrane CLI for managing user authentication and executing Google Gemini actions.\n- [EXTERNAL_DOWNLOADS]: Recommends the installation of the @membranehq/cli package. This is a legitimate tool provided by the vendor (membranedev) for interacting with their platform.\n- [PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks associated with processing external API data.\n
Ingestion points: Data returned from membrane action run commands is incorporated into the agent's context.\n
Boundary markers: No specific delimiters or markers are described in the integration examples.\n
Capability inventory: The agent has access to shell command execution through the membrane CLI.\n
Sanitization: The skill relies on the Membrane platform's internal handling of structured action outputs.

google-gemini