The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is the official command-line tool for the Membrane platform as specified by the author.
[COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to handle authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). These are standard operations for this platform integration.
[PROMPT_INJECTION]: The skill facilitates the processing of external data (SMS messages from Textline), which represents a surface for indirect prompt injection.
Ingestion points: Incoming message and conversation data retrieved from Textline via the CLI.
Boundary markers: None specified in the documentation.
Capability inventory: The skill can execute CLI commands and dynamically create new actions via the platform.
Sanitization: No explicit sanitization or instruction to escape message content is provided.
[DATA_EXFILTRATION]: The skill promotes secure credential management by using Membrane's server-side authentication flows, specifically advising against asking users for API keys or tokens.

textline