The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package globally via npm. This is a standard dependency for the tool's core functionality.
[COMMAND_EXECUTION]: Uses shell commands through the membrane CLI tool to perform various tasks, including authentication (membrane login), connection management (membrane connect), and action execution (membrane action run).
[PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by passing user-defined natural language intents and JSON input directly to CLI commands.
Ingestion points: User-provided values for the --intent and --input flags in SKILL.md.
Boundary markers: Not present; user input is interpolated directly into command arguments.
Capability inventory: Execution of pre-defined or dynamically generated actions via the Membrane platform's CLI.
Sanitization: No explicit sanitization or validation steps are described for the external content before it is processed.

sitespeakai