inworld-ai

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the Membrane CLI tool (@membranehq/cli) from the official npm registry to enable interaction with the Membrane platform.
  • [COMMAND_EXECUTION]: Executes shell commands via the Membrane CLI to perform authentication (membrane login), manage service connections (membrane connect), and run Inworld AI actions (membrane action run).
  • [COMMAND_EXECUTION]: Includes commands for dynamic action creation (membrane action create), where the Membrane platform generates and deploys integration logic based on a natural language description provided by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 08:34 AM
Security Audit — agent-trust-hub — inworld-ai