concepts/sandboxing.md Codex Docs, 2026-03-05 06:22 UTC → 2026-04-13 18:37 UTC

1# Sandbox

2 

3The sandbox is the boundary that lets Codex act autonomously without giving it

4unrestricted access to your machine. When Codex runs local commands in the

5**Codex app**, **IDE extension**, or **CLI**, those commands run inside a

6constrained environment instead of running with full access by default.

7 

8That environment defines what Codex can do on its own, such as which files it

9can modify and whether commands can use the network. When a task stays inside

10those boundaries, Codex can keep moving without stopping for confirmation. When

11it needs to go beyond them, Codex falls back to the approval flow.

12 

13Sandboxing and approvals are different controls that work together. The

14 sandbox defines technical boundaries. The approval policy decides when Codex

15 must stop and ask before crossing them.

16 

17## What the sandbox does

18 

19The sandbox applies to spawned commands, not just to Codex's built-in file

20operations. If Codex runs tools like `git`, package managers, or test runners,

21those commands inherit the same sandbox boundaries.

22 

23Codex uses platform-native enforcement on each OS. The implementation differs

24between macOS, Linux, WSL2, and native Windows, but the idea is the same across

25surfaces: give the agent a bounded place to work so routine tasks can run

26autonomously inside clear limits.

27 

28## Why it matters

29 

30The sandbox reduces approval fatigue. Instead of asking you to confirm every

31low-risk command, Codex can read files, make edits, and run routine project

32commands within the boundary you already approved.

33 

34It also gives you a clearer trust model for agentic work. You aren't just

35trusting the agent's intentions; you are trusting that the agent is operating

36inside enforced limits. That makes it easier to let Codex work independently

37while still knowing when it will stop and ask for help.

38 

39## Getting started

40 

41Codex applies sandboxing automatically when you use the default permissions

42mode.

43 

44### Prerequisites

45 

46On **macOS**, sandboxing works out of the box using the built-in Seatbelt

47framework.

48 

49On **Windows**, Codex uses the native [Windows

50sandbox](https://developers.openai.com/codex/windows#windows-sandbox) when you run in PowerShell and the

51Linux sandbox implementation when you run in WSL2.

52 

53On **Linux and WSL2**, install `bubblewrap` with your package manager first:

54 

55```bash

56sudo apt install bubblewrap

57```

58 

59```bash

60sudo dnf install bubblewrap

61```

62 

63Codex uses the first `bwrap` executable it finds on `PATH`. If no `bwrap`

64executable is available, Codex falls back to a bundled helper, but that helper

65requires support for unprivileged user namespace creation. Installing the

66distribution package that provides `bwrap` keeps this setup reliable.

67 

68Codex surfaces a startup warning when `bwrap` is missing or when the helper

69can't create the needed user namespace. On distributions that restrict this

70AppArmor setting, you can enable it with:

71 

72```bash

73sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0

74```

75 

76## How you control it

77 

78Most people start with the permissions controls in the product.

79 

80In the Codex app and IDE, you choose a mode from the permissions selector under

81the composer or chat input. That selector lets you rely on Codex's default

82permissions, switch to full access, or use your custom configuration.

83 

84![Codex app permissions selector showing Default permissions, Full access, and Custom (config.toml)](/images/codex/app/permissions-selector-light.webp)

85 

86In the CLI, use [`/permissions`](https://developers.openai.com/codex/cli/slash-commands#update-permissions-with-permissions)

87to switch modes during a session.

88 

89## Configure defaults

90 

91If you want Codex to start with the same behavior every time, use a custom

92configuration. Codex stores those defaults in `config.toml`, its local settings

93file. [Config basics](https://developers.openai.com/codex/config-basic) explains how it works, and the

94[Configuration reference](https://developers.openai.com/codex/config-reference) documents the exact keys for

95`sandbox_mode`, `approval_policy`, and

96`sandbox_workspace_write.writable_roots`. Use those settings to decide how much

97autonomy Codex gets by default, which directories it can write to, and when it

98should pause for approval.

99 

100At a high level, the common sandbox modes are:

101 

102- `read-only`: Codex can inspect files, but it can't edit files or run

103 commands without approval.

104- `workspace-write`: Codex can read files, edit within the workspace, and run

105 routine local commands inside that boundary. This is the default low-friction

106 mode for local work.

107- `danger-full-access`: Codex runs without sandbox restrictions. This removes

108 the filesystem and network boundaries and should be used only when you want

109 Codex to act with full access.

110 

111The common approval policies are:

112 

113- `untrusted`: Codex asks before running commands that aren't in its trusted

114 set.

115- `on-request`: Codex works inside the sandbox by default and asks when it

116 needs to go beyond that boundary.

117- `never`: Codex doesn't stop for approval prompts.

118 

119Full access means using `sandbox_mode = "danger-full-access"` together with

120`approval_policy = "never"`. By contrast, `--full-auto` is the lower-risk local

121automation preset: `sandbox_mode = "workspace-write"` and

122`approval_policy = "on-request"`.

123 

124If you need Codex to work across more than one directory, writable roots let

125you extend the places it can modify without removing the sandbox entirely. If

126you need a broader or narrower trust boundary, adjust the default sandbox mode

127and approval policy instead of relying on one-off exceptions.

128 

129For reusable permission sets, set `default_permissions` to a named profile and

130define `[permissions.<name>.filesystem]` or `[permissions.<name>.network]`.

131Managed network profiles use map tables such as

132`[permissions.<name>.network.domains]` and

133`[permissions.<name>.network.unix_sockets]` for domain and socket rules.

134 

135When a workflow needs a specific exception, use [rules](https://developers.openai.com/codex/rules). Rules

136let you allow, prompt, or forbid command prefixes outside the sandbox, which is

137often a better fit than broadly expanding access. For a higher-level overview

138of approvals and sandbox behavior in the app, see

139[Codex app features](https://developers.openai.com/codex/app/features#approvals-and-sandboxing), and for the

140IDE-specific settings entry points, see [Codex IDE extension settings](https://developers.openai.com/codex/ide/settings).

141 

142Platform details live in the platform-specific docs. For native Windows setup,

143behavior, and troubleshooting, see [Windows](https://developers.openai.com/codex/windows). For admin

144requirements and organization-level constraints on sandboxing and approvals, see

145[Agent approvals & security](https://developers.openai.com/codex/agent-approvals-security).