agent-approvals-security diff

agent-approvals-security.md +26 −17

Details

24- **Codex cloud**: Runs in isolated OpenAI-managed containers, preventing access to your host system or unrelated data. Uses a two-phase runtime model: setup runs before the agent phase and can access the network to install specified dependencies, then the agent phase runs offline by default unless you enable internet access for that environment. Secrets configured for cloud environments are available only during setup and are removed before the agent phase starts.24- **Codex cloud**: Runs in isolated OpenAI-managed containers, preventing access to your host system or unrelated data. Uses a two-phase runtime model: setup runs before the agent phase and can access the network to install specified dependencies, then the agent phase runs offline by default unless you enable internet access for that environment. Secrets configured for cloud environments are available only during setup and are removed before the agent phase starts.

25- **Codex CLI / IDE extension**: OS-level mechanisms enforce sandbox policies. Defaults include no network access and write permissions limited to the active workspace. You can configure the sandbox, approval policy, and network settings based on your risk tolerance.25- **Codex CLI / IDE extension**: OS-level mechanisms enforce sandbox policies. Defaults include no network access and write permissions limited to the active workspace. You can configure the sandbox, approval policy, and network settings based on your risk tolerance.

26 26

~~27In the `Auto` preset (for example, `--full-auto`), Codex can read files, make edits, and run commands in the working directory automatically.~~27In the `Auto` preset (for example, `--sandbox workspace-write --ask-for-approval on-request`), Codex can read files, make edits, and run commands in the working directory automatically.

28 28

29Codex asks for approval to edit files outside the workspace or to run commands that require network access. If you want to chat or plan without making changes, switch to `read-only` mode with the `/permissions` command.29Codex asks for approval to edit files outside the workspace or to run commands that require network access. If you want to chat or plan without making changes, switch to `read-only` mode with the `/permissions` command.

30 30

31Codex can also elicit approval for app (connector) tool calls that advertise side effects, even when the action isn't a shell command or file change. Destructive app/MCP tool calls always require approval when the tool advertises a destructive annotation, even if it also advertises other hints (for example, read-only hints).31Codex can also elicit approval for app (connector) tool calls that advertise side effects, even when the action isn't a shell command or file change. Destructive app/MCP tool calls always require approval when the tool advertises a destructive annotation, even if it also advertises other hints (for example, read-only hints).

32 32

~~33## Network access [Elevated Risk](https://help.openai.com/articles/20001061)~~33## Network access <ElevatedRiskBadge class="ml-2" />

34 34

35For Codex cloud, see [agent internet access](https://developers.openai.com/codex/cloud/internet-access) to enable full internet access or a domain allow list.35For Codex cloud, see [agent internet access](https://developers.openai.com/codex/cloud/internet-access) to enable full internet access or a domain allow list.

36 36

121approvals_reviewer = "auto_review"121approvals_reviewer = "auto_review"

122```122```

123 123

124For the full reviewer lifecycle, trigger conditions, configuration precedence,

125and failure behavior, see

126[Auto-review](https://developers.openai.com/codex/concepts/sandboxing/auto-review).

127

124The reviewer evaluates only actions that already need approval, such as sandbox128The reviewer evaluates only actions that already need approval, such as sandbox

125escalations, network requests, `request_permissions` prompts, or side-effecting129escalations, blocked network requests, `request_permissions` prompts, or

126app and MCP tool calls. Actions that stay inside the sandbox continue without an130side-effecting app and MCP tool calls. Actions that stay inside the sandbox

127extra review step.131continue without an extra review step.

128 132

129The reviewer policy checks for data exfiltration, credential probing, persistent133The reviewer policy checks for data exfiltration, credential probing, persistent

130security weakening, and destructive actions. Low-risk and medium-risk actions134security weakening, and destructive actions. Low-risk and medium-risk actions

131can proceed when policy allows them. The policy denies critical-risk actions.135can proceed when policy allows them. The policy denies critical-risk actions.

132High-risk actions require enough user authorization and no matching deny rule.136High-risk actions require enough user authorization and no matching deny rule.

133Timeouts, parse failures, and review errors fail closed.137Prompt-build, review-session, and parse failures fail closed. Timeouts are

138surfaced separately, but the action still does not run.

134 139

135The [default reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)140The [default reviewer policy](https://github.com/openai/codex/blob/main/codex-rs/core/src/guardian/policy.md)

136is in the open-source Codex repository. Enterprises can replace its141is in the open-source Codex repository. Enterprises can replace its

139take precedence. For setup details, see144take precedence. For setup details, see

140[Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration#configure-automatic-review-policy).145[Managed configuration](https://developers.openai.com/codex/enterprise/managed-configuration#configure-automatic-review-policy).

141 146

142In the Codex app, these reviews appear as automatic review items with a status such147In the Codex app, these reviews appear as automatic review items with a status

143as Reviewing, Approved, Denied, Stopped, or Timed out. They can also include a148such as Reviewing, Approved, Denied, Aborted, or Timed out. They can also

144risk level for the reviewed request.149include a risk level and user-authorization assessment for the reviewed

150request.

145 151

146Automatic review uses extra model calls, so it can add to Codex usage. Admins152Automatic review uses extra model calls, so it can add to Codex usage. Admins

147can constrain it with `allowed_approvals_reviewers`.153can constrain it with `allowed_approvals_reviewers`.

148 154

149### Common sandbox and approval combinations155### Common sandbox and approval combinations

150 156

152| ----------------------------------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------ |158| ----------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |

153| Auto (preset) | *no flags needed* or `--full-auto` | Codex can read files, make edits, and run commands in the workspace. Codex requires approval to edit outside the workspace or to access network. |159| Auto (preset) | _no flags needed_ or `--sandbox workspace-write --ask-for-approval on-request` | Codex can read files, make edits, and run commands in the workspace. Codex requires approval to edit outside the workspace or to access network. |

154| Safe read-only browsing | `--sandbox read-only --ask-for-approval on-request` | Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network. |160| Safe read-only browsing | `--sandbox read-only --ask-for-approval on-request` | Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network. |

156| Automatically edit but ask for approval to run untrusted commands | `--sandbox workspace-write --ask-for-approval untrusted` | Codex can read and edit files but asks for approval before running untrusted commands. |162| Automatically edit but ask for approval to run untrusted commands | `--sandbox workspace-write --ask-for-approval untrusted` | Codex can read and edit files but asks for approval before running untrusted commands. |

157| Dangerous full access | `--dangerously-bypass-approvals-and-sandbox` (alias: `--yolo`) | [Elevated Risk](https://help.openai.com/articles/20001061) No sandbox; no approvals *(not recommended)* |163| Auto-review mode | `--sandbox workspace-write --ask-for-approval on-request -c approvals_reviewer=auto_review` or `approvals_reviewer = "auto_review"` | Same sandbox boundary as standard on-request mode, but eligible approval requests are reviewed by Auto-review instead of surfacing to the user. |

164| Dangerous full access | `--dangerously-bypass-approvals-and-sandbox` (alias: `--yolo`) | <ElevatedRiskBadge /> No sandbox; no approvals _(not recommended)_ |

158 165

159`--full-auto` is a convenience alias for `--sandbox workspace-write --ask-for-approval on-request`.166For non-interactive runs, use `codex exec --sandbox workspace-write`; Codex keeps older `codex exec --full-auto` invocations as a deprecated compatibility path and prints a warning.

160 167

161With `--ask-for-approval untrusted`, Codex runs only known-safe read operations automatically. Commands that can mutate state or trigger external execution paths (for example, destructive Git operations or Git output/config-override flags) require approval.168With `--ask-for-approval untrusted`, Codex runs only known-safe read operations automatically. Commands that can mutate state or trigger external execution paths (for example, destructive Git operations or Git output/config-override flags) require approval.

162 169

202 209

203```bash210```bash

204# macOS211# macOS

205codex sandbox macos [--full-auto] [--log-denials] [COMMAND]...212codex sandbox macos [--permissions-profile <name>] [--log-denials] [COMMAND]...

206# Linux213# Linux

207codex sandbox linux [--full-auto] [COMMAND]...214codex sandbox linux [--permissions-profile <name>] [COMMAND]...

215# Windows

216codex sandbox windows [--permissions-profile <name>] [COMMAND]...

208```217```

209 218

210The `sandbox` command is also available as `codex debug`, and the platform helpers have aliases (for example `codex sandbox seatbelt` and `codex sandbox landlock`).219The `sandbox` command is also available as `codex debug`, and the platform helpers have aliases (for example `codex sandbox seatbelt` and `codex sandbox landlock`).

266 275

2671. Install Visual Studio Code and the [Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).2761. Install Visual Studio Code and the [Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers).

2682. Copy the Codex example `.devcontainer` setup into your repository, or start from the Codex repository directly.2772. Copy the Codex example `.devcontainer` setup into your repository, or start from the Codex repository directly.

2693. In VS Code, run **Dev Containers: Open Folder in Container…** and select `.devcontainer/devcontainer.secure.json`.2783. In VS Code, run **Dev Containers: Open Folder in Container...** and select `.devcontainer/devcontainer.secure.json`.

2704. After the container starts, open a terminal and run `codex`.2794. After the container starts, open a terminal and run `codex`.

271 280

272You can also start the container from the CLI:281You can also start the container from the CLI:

agent-approvals-security.md Codex Docs, 2026-04-25 06:37 UTC → 2026-05-14 07:00 UTC