The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package globally via npm and uses npx to execute commands. These are official tools and registries associated with the skill's author (membranedev).
[COMMAND_EXECUTION]: Executes several membrane CLI commands to handle authentication, connection setup, action discovery, and execution. These commands are standard for the integration's functionality and do not involve suspicious parameters or privilege escalation.
[SAFE]: No indicators of obfuscation, data exfiltration, or persistence were found. The skill promotes security best practices by delegating credential management to the Membrane platform instead of requesting local storage of API keys.
[SAFE]: The use of natural language intents to discover or create actions through the Membrane CLI is a legitimate functional feature of the platform and does not present a malicious prompt injection risk in this context.

airship