The Agent Skills Directory

[SAFE]: The skill utilizes the @membranehq/cli for all interactions, which is the official tool provided by the vendor.
[SAFE]: Secret management is handled through a managed authentication flow (membrane login, membrane connect), ensuring that API keys and tokens are not stored or processed within the skill instructions or the agent's prompt history.
[SAFE]: No obfuscation, prompt injection attempts, or unauthorized data exfiltration patterns were detected in the instructions or metadata.

geckoboard