Permission Presets and the Sandbox
Module 2 · Delegation

Permission Presets and the Sandbox

Match agent autonomy to risk with Antigravity's permission presets (Request Review, Default, Auto, Turbo), allow, ask, and deny rules, and the terminal sandbox, and learn from the Turbo-mode incident that wiped a user's drive.

A Cautionary Tale

In December 2025, a user reported that Antigravity, running in Turbo mode, which ran terminal commands without asking, had erased an entire drive. They had asked the agent to clear a project’s cache. The delete command targeted the root of the drive instead of the project folder, and it bypassed the Recycle Bin. The Register and other outlets covered the story.

The agent made a mistake that a person could also make. What turned a mistake into a disaster was that nothing stood between the mistaken command and the disk: no approval prompt, no sandbox, no deny rule. That’s a delegation failure, and it’s the subject of this lesson.


The Desktop App’s Permission Presets

As of November 2026, the Antigravity desktop app has four presets covering terminal commands, file access, MCP tools, and web page reads:

  1. 1 Request Review

    Every command needs approval

  2. 2 Default

    Sandbox runs free; sensitive asks

  3. 3 Auto

    Automatic check of risky steps

  4. 4 Turbo

    No restrictions

PresetHow it behavesGood fit
Request ReviewEvery command requires your approval.Unfamiliar or untrusted repos; learning the tool; sensitive work.
DefaultAsks before sensitive operations. Commands that stay inside the terminal sandbox run without asking; anything that would leave the sandbox needs approval.Most everyday work.
Auto (in preview as of this writing)Commands that would leave the sandbox are checked automatically: safe, reversible ones proceed and risky ones pause for you.Longer runs on recoverable work, once you trust your rules.
TurboRuns all commands without restrictions, with full filesystem access.Only inside a disposable VM or container with nothing valuable in reach, if at all.

You can set a preset globally, per project, or from the picker in the message box. Business and enterprise accounts may see an older set of settings, such as “Terminal command auto execution”, with options like Require Review, Proceed in Sandbox, and Always Proceed. The logic is the same.

The CLI has its own equivalents: agent modes (such as default, auto, accept-edits, and plan) and a tool-permission setting. Its high-autonomy flag, --dangerously-skip-permissions, names the risk plainly.


Rules on Top of Presets

Presets set the overall level. Allow, ask, and deny rules let you be specific, and Antigravity’s documentation says your rules always take precedence over the preset.

  • Allow the frequent, safe commands: your test runner, linter, and formatter. Fewer prompts means you’ll actually read the ones that remain.
  • Ask for anything that leaves your machine or can’t be undone: git push, deploy scripts, package publishing.
  • Deny anything that should never happen: recursive deletes outside the project, commands that touch credentials.

A short deny list would have stopped the drive-wipe incident: no matter which preset was active, a recursive delete at a drive root would have been blocked.


The Sandbox

Antigravity’s terminal sandbox limits what commands can reach at the operating-system level. In recent versions, for example, sandboxed commands can’t read folders like ~/.docker or ~/.kube unless you grant access. Two related settings matter:

  • Non-workspace file access lets agents read and write outside the project folder. Google’s docs say to enable it “with caution”. Leave it off unless a task truly needs it.
  • Browser allowlists and denylists control which sites the agent’s browser may visit. That matters for safety, as module 5 explains.

The Default preset leans on the sandbox: commands run freely because they’re contained. Turbo removes that containment.

YOUR MACHINETERMINAL SANDBOXWorkspaceyour project folder~/.ssh · ~/.kube · cloud CLIsother projects · browser profilesLEAVING THE SANDBOX?Request ReviewDefaultAutoTurboyou approve every commandyou approvean automatic check decidesno boundary; nothing checksDeny rules apply under every preset.
⚠️ Common Pitfall: Turbo as a Comfort Setting

Common mistake: switching to Turbo because approval prompts are annoying, then leaving it on for every project.

Prompts are annoying when they’re about boring, safe commands. The fix is allow rules for those commands, not removing every checkpoint. Keep high-autonomy presets for isolated environments where the worst case is “rebuild the VM.”


Choosing a Preset per Task

TaskPresetPlus
Exploring a repo you just cloned from the internetRequest ReviewSandbox on, non-workspace access off
Implementing an approved plan in your own repoDefaultAllow rules for test and lint
A long refactor in a disposable dev containerAuto, or Turbo inside the containerCommit often; review the full diff
Anything near deploy scripts or production configRequest ReviewAsk rules on deploy commands
A scheduled automationDefault or stricterRead-only scope to start

Remember from the last lesson: approvals you grant in a conversation also apply to its subagents. A broad “always allow” reaches further than one agent.

🧪 Try It: Set Your Dials

For one project:

  1. Choose its default preset and write down why.
  2. Write five allow rules for safe, frequent commands.
  3. Write three ask rules for commands that leave your machine or can’t be undone.
  4. Write three deny rules for commands that should never run, including a recursive delete outside the project.
  5. Confirm non-workspace file access is off, and check which preset your scheduled automations use.
🧠 Knowledge Check

1. In the reported December 2025 drive-wipe incident, what turned an agent's mistake into a disaster?

2. In the Default preset, why can most commands run without asking?

3. Your rules deny a command, but your preset is Turbo. What happens, according to Antigravity's docs?

4. You approve 'always allow' for a command in a conversation that has subagents. What should you keep in mind?


Up Next

Module 3 is Description: briefing agents, choosing models, and building lasting context with rules and skills.