Skip to main content
The sandbox command allows you to manually execute commands within the same sandbox environment that Codex uses for command execution.

​
Usage

​
Description

This command is primarily used for testing and debugging sandbox behavior. It runs the specified command with the same security restrictions that Codex applies when executing commands on your behalf. The sandbox environment varies by platform:
  • Linux: Landlock LSM + seccomp filters (or Bubblewrap if enabled)
  • macOS: Seatbelt sandbox profiles
  • Windows: Restricted token with limited privileges

​
Options

​
--sandbox
string
Sandbox mode to use. Options: read-only, workspace-write, danger-full-accessDefault: read-only
​
--cwd
string
Working directory for the command.Default: current directory

​
Examples

​
Run Command in Read-Only Sandbox

​
Test Workspace Write Access

​
Run in Specific Directory

​
Test Network Restrictions

​
Sandbox Modes

​
read-only

  • Read access to workspace files
  • No write access
  • No network access
  • Cannot modify system files

​
workspace-write

  • Read access to workspace files
  • Write access within workspace directory
  • No network access
  • Cannot modify system files outside workspace

​
danger-full-access

  • Full file system access
  • Network access allowed
  • Can modify any accessible files
  • Use with caution

​
Use Cases

​
Testing Sandbox Policies

Verify that your sandbox configuration works as expected:

​
Debugging Command Failures

When a command fails in Codex, test it manually:

​
Validating Execpolicy Rules

Test whether a command would be allowed:

​
Exit Codes

The command returns the exit code of the executed command.

​
Security Notes

The danger-full-access sandbox mode disables most security restrictions. Only use it when you fully trust the command being executed.
Sandbox behavior may vary between platforms. Always test critical workflows on your target platform.

Sandboxing Concepts

Learn about Codex sandboxing

Exec Policies

Configure execution policies