8746in the Codex desktop app. Codex performs scan analysis in a regular task, while8746in the Codex desktop app. Codex performs scan analysis in a regular task, while
8747the workbench keeps the scan and its results available when you return.8747the workbench keeps the scan and its results available when you return.
8748 8748
8749In the ChatGPT desktop app, open the ChatGPT dropdown and select **Codex**.
8749Install and enable the [Codex Security plugin](https://learn.chatgpt.com/docs/security/plugin), then8750Install and enable the [Codex Security plugin](https://learn.chatgpt.com/docs/security/plugin), then
8750select **Security** in the desktop-app sidebar.8751select **Security** in the sidebar.
8751 8752
8752If **Security** doesn't appear, confirm that the plugin is installed and8753If **Security** doesn't appear, confirm that **Codex** is selected and the
8753enabled. Update the desktop app and plugin if needed, and check whether your8754plugin is installed and enabled. Update the desktop app and plugin if needed,
8754workspace administrator allows the plugin.8755and check whether your workspace administrator allows the plugin.
8755 8756
8756#### Start a scan8757#### Start a scan
8757 8758
8924 8925
8925Codex 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.8926Codex 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.
8926 8927
8927Codex 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).8928Codex 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 (unless the tool advertises a read annotation, which takes priority).
8928 8929
8929#### Network access8930#### Network access
8930 8931
10826 10827
10827#### Use Codex Security in the desktop app10828#### Use Codex Security in the desktop app
10828 10829
10830In the ChatGPT desktop app, open the ChatGPT dropdown and select **Codex**.
10829Install and enable the Codex Security plugin to open **Security** in the10831Install and enable the Codex Security plugin to open **Security** in the
10830desktop-app sidebar. The Security workbench keeps your scans, findings, and10832sidebar. The Security workbench keeps your scans, findings, and repositories in
10831repositories in one place while Codex runs each scan in a task.10833one place while Codex runs each scan in a task.
10832 10834
10833- Use **Scans** to start scans, follow their progress, and review saved results.10835- Use **Scans** to start scans, follow their progress, and review saved results.
10834- Use **Findings** to inspect issues and evidence across completed scans.10836- Use **Findings** to inspect issues and evidence across completed scans.
