expensify

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the official vendor CLI (@membranehq/cli) to manage authentication and execute actions. This approach minimizes the risk of credential exposure as it avoids direct handling of API keys by the agent or user instructions.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI from the official NPM registry (@membranehq/cli). As this is a well-known package registry and the package belongs to the vendor's namespace, it is considered a safe and standard installation procedure.
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands to interact with the Membrane CLI. These commands (login, connect, action list, action run) are scoped to the intended functionality of managing Expensify data and do not involve suspicious privilege escalation or system-level modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:38 PM