The Agent Skills Directory

[SAFE]: The skill utilizes official vendor tools (@membranehq/cli) to interact with external APIs, which is consistent with its stated purpose of providing Clear Books integration.
[SAFE]: Authentication is handled through a secure login flow that redirects to the vendor's platform, ensuring that no raw API keys or tokens are hardcoded or stored within the skill context.
[SAFE]: All command-line operations are restricted to the Membrane CLI and standard package management (npm), with no evidence of unauthorized privilege escalation, persistence mechanisms, or data exfiltration attempts.

clear-books