For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Codex Security plugin quickstart

Install the Codex Security plugin, run your first read-only scan, and review the result in Codex.

Install the Codex Security plugin, run a standard scan of a local repository, and review its findings. The scan leaves your source unchanged and saves a report with evidence and remediation guidance.

This page covers the Codex Security plugin in the desktop app or Codex CLI. To scan a connected GitHub repository in Codex cloud, install the separate Codex Security Cloud plugin from the plugin marketplace. See Cloud setup.

Install the plugin

  1. Open Codex in the ChatGPT desktop app.

  2. Open Plugins, search for Codex Security, or use the button below:

  3. Confirm the plugin is enabled, then open Security in the sidebar.

If Security doesn’t appear in the desktop-app sidebar, confirm that Codex is selected and the plugin is enabled. Update the app and plugin if needed, and check whether your workspace administrator allows the plugin.

Run your first scan

For the best scan quality, use gpt-5.6-sol with xhigh reasoning effort.

Choose a repository and configure a new security scan before you start it.

  1. Open the scan setup

    Select Security in the sidebar, open Scans, and select + Scan.

  2. Choose the codebase and scan area

    Select an existing repository or use another folder. Choose Codebase, leave Deep scan off, and select the entire repository or one folder. Confirm that the branch and revision identify the code you intended to scan.

  3. Add security context

    Choose the model and reasoning effort. Open Additional context only when you need to describe an attack vector, security-sensitive area, or repository detail that should guide the review.

    Turn on additional context to describe attack vectors, focus areas, and relevant security guidance.

  4. Start the scan

    Select Start scan and follow the scan phases in the Security workbench. Select View activity to inspect the Codex task that performs the scan.

  5. Review the result

    Open the completed scan to inspect findings, coverage, and available report artifacts. Use Findings to review issues across scans or Repositories to inspect a repository’s scan history.

    Review scan results, findings, and coverage in the Security workbench.

Interpret the result

Check the target and revision first. Then read which areas were reviewed and which were deferred. A completed scan can still have coverage gaps. A review that reports no findings hasn’t necessarily ruled out every vulnerability.

Open a finding and read its source evidence, attacker prerequisites, validation, and remaining uncertainty. Validation can use source analysis without running a reproducer. Use the recorded method and evidence to decide whether the issue applies to your system.

What the scan creates

In the desktop app, completed scans remain in Scans. In Codex CLI, use the scan directory reported in the conversation. Open report.md for the readable result. Detailed vulnerability reports under findings/ and design proposals under hardening/ are optional outputs you can request.

The directory also contains scan-manifest.json, findings.json, and coverage.json for tools and automation. Keep it together when sharing or archiving results so the report’s links continue to work.

Choose your next workflow

For other scan modes and workflows, return to the Codex Security overview.