The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Membrane CLI (membrane) to perform administrative and data tasks. These commands include login, connect, action run, and request. All commands are within the expected scope of a management integration and interact with the vendor's platform.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install @membranehq/cli from the NPM registry. This package belongs to the vendor's official ecosystem and is used for platform interactions.
[CREDENTIALS_UNSAFE]: The skill demonstrates best practices by explicitly advising against asking for API keys or tokens. It utilizes Membrane's connection system to handle OAuth and credential refreshing server-side, reducing the risk of secret exposure.
[DATA_EXFILTRATION]: While the skill can read and write data to Built Accounting, all operations are routed through the authenticated Membrane proxy. No unauthorized data exfiltration patterns or suspicious third-party domains were detected.

built-accounting