Overview
The gateway enforces security policies that control what the agent can do. This includes sandboxing command execution, restricting tool access, and requiring user approval for dangerous operations.Security Modes
- Unrestricted
- Sandboxed (Default)
- Locked
All tools are available with no approval required. Suitable for trusted environments where the agent has full system access.
Tool Policies
Fine-grained control over individual tools:Policy Modes
Exec Approval Flow
When the agent requests a command that requires approval:1
Command displayed
The command is displayed to the user (in dashboard or channel)
2
User reviews
User reviews the command
3
User decides
User approves or rejects
4
Execution or alternative
If approved, the command executes normally. If rejected, the agent is informed and can try an alternative.
Gateway Authentication
Recommendations
Personal use
Sandboxed mode with approval for destructive commands
Team use
Sandboxed mode with restricted paths
Customer-facing
Locked mode with only safe tools
Development
Unrestricted mode for rapid iteration
