Codex sandbox modes: read-only, workspace-write, danger-full-access and network access
How do I change the Codex sandbox mode and allow network access?
Codex has three sandbox modes: read-only, workspace-write and danger-full-access. Pick one per run with codex --sandbox <mode>, or set sandbox_mode in ~/.codex/config.toml. Network access is off by default in workspace-write; turn it on with network_access = true under [sandbox_workspace_write].
Compare: allow all commands in every AI coding agent →
Compare: sandbox modes in every AI coding agent →
The three sandbox modes
- read-only: Codex can inspect files but cannot edit files or run commands without approval.
- workspace-write: Codex can read files, edit inside the workspace and run routine local commands there. This is the default low-friction mode for local work. Network access is off by default.
- danger-full-access: no sandbox. Filesystem and network limits are removed. OpenAI marks it as elevated risk and not recommended.
Set the mode for one run
Edit the workspace, ask before leaving it
codex --sandbox workspace-write --ask-for-approval on-request
Read only, for browsing or planning
codex --sandbox read-only --ask-for-approval on-request
Read only in CI, never prompt
codex --sandbox read-only --ask-for-approval never
Inside a session you can switch to read-only with the /permissions command.
Set a default in config.toml
sandbox_mode accepts read-only, workspace-write or danger-full-access. Extra keys under [sandbox_workspace_write] apply only in workspace-write mode.
~/.codex/config.toml
sandbox_mode = "workspace-write" approval_policy = "on-request" [sandbox_workspace_write] network_access = true writable_roots = ["/path/to/another/folder"]
- network_access: allow outbound network access inside the workspace-write sandbox.
- writable_roots: extra folders Codex may write to.
- exclude_tmpdir_env_var: remove $TMPDIR from writable roots.
- exclude_slash_tmp: remove /tmp from writable roots.
Paths that stay read-only
Even in workspace-write, some folders inside a writable root stay read-only, including everything under them:
- <writable_root>/.git, whether it is a folder or a file. If it is a gitdir pointer file, the real Git folder is protected too.
- <writable_root>/.agents when it exists as a folder.
- <writable_root>/.codex when it exists as a folder.
How each platform enforces it
- macOS: the built-in Seatbelt framework. It works out of the box.
- Linux and WSL2: bubblewrap (bwrap). Codex uses the first bwrap on PATH and otherwise falls back to a bundled helper that needs unprivileged user namespace support.
- Windows: the native Windows sandbox in PowerShell, and the Linux sandbox in WSL2.
Sources
More Codex guides
- Codex CLI: approval and sandbox modes (and what --yolo does)
- Configure Codex with config.toml
- Codex AGENTS.md: global, project and override instruction files explained
- Codex MCP servers: codex mcp add and [mcp_servers] in config.toml
- codex exec: run Codex non-interactively in scripts and CI with JSON output
- Codex skills: create SKILL.md, skill folder locations and $skill invocation
- Codex hooks: hooks.json, PreToolUse allow/deny, exit code 2 and config.toml [hooks]
Reviewed Oct 18, 2026. Settings change often; the linked vendor docs are the source of truth.
Built an MCP server? Get it listed everywhere →
Shipping an Android app? Google Play needs 12 testers for 14 days first. Get them with Tester Exchange →