Skills
skills/membranedev/application-skills/cumulio/Gen Agent Trust Hub

cumulio

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package via npm. This is an official vendor resource used to facilitate communication with the platform.
  • [COMMAND_EXECUTION]: Instructions include various shell commands using the membrane CLI, such as membrane login, membrane connect, and membrane action run. These are used for legitimate administrative and integration tasks.
  • [CREDENTIALS_UNSAFE]: The skill promotes secure authentication practices by utilizing the platform's native connection and token management system, explicitly advising against manual API key handling within the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:43 AM