AI Explainedby Milad Fahmy

AI Explained

Agent sandboxing and permissions

Your coding agent ran a command you never read. What stopped it from wiping your home folder? Permissions decide what it may do; a sandbox limits what it can do.

Milad FahmyNov 7, 20262 min read

On this page
  1. Permissions: allow, ask, deny
  2. Sandboxes: the OS says no
  3. Why it matters: the lethal trifecta
  4. Skipping prompts entirely?
  5. A sensible setup

Your coding agent just ran a command you never read. What stopped it from wiping your home folder? Two things keep agents in check: permissions decide what an agent may do, and a sandbox limits what it can do.

Permissions: allow, ask, deny

Permissions are the prompts you already know: allow this command, or ask me first. You write them as rules:

{
  "permissions": {
    "allow": ["Bash(npm run test)"],
    "ask":   ["Bash(git commit:*)"],
    "deny":  ["Bash(git push:*)"]
  }
}

In Claude Code, rules are checked in order: deny, then ask, then allow, so a broad deny always wins.

The weakness: too many prompts cause fatigue. By the fiftieth one, you click "yes" without reading.

Sandboxes: the OS says no

A sandbox is the other layer. The operating system itself blocks what the agent can't touch:

  • Filesystem isolation: the agent can only read and write inside the folders you allow, like your project.
  • Network isolation: it can only reach approved servers, like your package registry.

You need both. Anthropic points out that without network limits, a hijacked agent could simply upload your SSH keys.

Claude Code builds its sandbox into the OS: bubblewrap on Linux and Seatbelt on macOS. Anthropic says sandboxing cut permission prompts by 84% in its internal use, because safe actions inside the sandbox no longer need asking.

Why it matters: the lethal trifecta

Simon Willison describes a dangerous combination he calls the lethal trifecta:

  1. access to your private data,
  2. exposure to untrusted content (like a web page or an email),
  3. a way to send data out.

Give an agent all three, and one malicious web page can trick it into leaking your data. The fix: remove one leg. A sandbox with no open network removes the third.

Skipping prompts entirely?

Some tools let you bypass all permission prompts. Only do that inside a container or VM you can throw away.

A sensible setup

  • Sandbox by default.
  • Allow your safe, frequent commands (tests, linting, builds).
  • Deny anything that pushes, deploys or deletes.

Ask less, but limit more.

Sources

#agent sandboxing#permissions#ai security#coding agents#claude code

Watch