The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user/agent to install the @membranehq/cli package from the NPM registry. This is the official command-line tool provided by the vendor (membranedev/membranehq) for interacting with their platform.
[COMMAND_EXECUTION]: Utilizes the membrane CLI to manage connections and execute actions. These commands are restricted to the functionality provided by the vendor's platform.
[CREDENTIALS_UNSAFE]: The skill explicitly adheres to security best practices by instructing the agent to never request API keys or tokens from the user, instead relying on the platform's built-in OAuth and connection management.
[DATA_EXPOSURE]: This skill provides a surface for indirect prompt injection by interpolating user-provided intents and inputs directly into CLI commands (e.g., membrane action list --intent "QUERY"). While this is a common pattern for such tools, it relies on the underlying CLI and LLM guardrails to prevent command injection or unintended behavior.

polygon