PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

OpenAI Codex Security: Automated Vulnerability Discovery, Validation, and Remediation CLI & SDK

github.com | tool | #ai-security | #devsecops | #sast | #defense | #vulnerability-remediation | #cli | #openai | #sdk | #codex-security
🔗 Original ↗

Summary

OpenAI's Codex Security (@openai/codex-security) is a CLI and TypeScript SDK for finding, validating, and fixing code vulnerabilities, featuring containerized bulk scans and embedding-based dedup.

Why it matters

Represents OpenAI's official expansion into DevSecOps and AI-driven security analysis, providing end-to-end automated vulnerability triage and repair pipelines.
Published
Collected

📦 Full-Text Content Snapshot

R2 Archive · Full Article Preserved200 lines · 9.5 KB
📄 Raw .md⬇️ Download .md

Codex Security helps you find, investigate, and fix vulnerabilities in your code. Use its security workflows in Codex, or automate them with the @openai/codex-security CLI and TypeScript SDK.

Source: github.com/openai/codex-security · Published: 2026-08-28T13:51:50Z

Features

  • Scan repositories, selected paths, or Git changes. Deep scans run parallel discovery workers on repositories and selected paths.
  • Validate candidate findings, generate patches, and verify existing fixes.
  • Draft SECURITY.md policies and save threat models for later review.
  • Browse saved scans and findings, identify duplicates, assess severity against your own rubric, and suggest owners from source and Git history.
  • Import GitHub code scanning alerts, export SARIF, JSON, or CSV, and publish findings to Linear or a findings service.
  • Automate scans across repositories or project components, including in CI and containers.

Use in Codex

Open your repository in a Codex session with the Codex Security plugin enabled, then ask:

Run a Codex Security scan on this repository, focusing on authentication and authorization. Return the saved report, source evidence, and coverage limits.

A completed scan saves a report, findings, coverage, and a threat model when available. Use those results to investigate findings, request a patch, or verify an existing fix. See the agent workflow guide for plugin setup, task selection, and recovery when required tools are unavailable.

Quick start

Requires Node.js 22.13.0+ within 22.x, or Node.js 24.x or 26.x, and Python 3.10+. Python 3.10 also requires tomli.

Install the CLI globally and sign in:

bash
npm install --global @openai/codex-security
cs login

cs is a short alias for codex-security; both commands run the same CLI. The installation creates both commands in npm's global executable directory, which must be on your PATH. If cs already resolves to another tool, use codex-security instead. If npm stops with an EEXIST error for cs, use npx @openai/codex-security without a global installation.

Run your scan from the repository directory:

bash
cs scan .

If you have Daybreak Blue access, add --cyber-access-program daybreak_blue to the scan command. Otherwise, omit the flag or use --cyber-access-program standard.

To use Codex's Daybreak toggle, pass --codex daybreak=true. It defaults off and requires compatible access. See Daybreak configuration for SDK and plugin usage, including Deep Scan workers.

Scans use your existing SECURITY.md guidance. You can optionally draft or update a policy before scanning.

To run without a global installation, replace cs in these examples with npx @openai/codex-security, for example:

bash
npx @openai/codex-security scan .

For CI, set OPENAI_API_KEY or CODEX_API_KEY in the scan process's environment. On remote or headless machines, use login --device-auth if your workspace allows it, or sign in over SSH.

Some cybersecurity requests and protected findings require Trusted Access for Cyber approval.

Scan options

Choose a scope and scan mode:

bash
# Scan selected paths.
cs scan . --path src --path tests

# Scan committed changes from a base revision to HEAD.
cs scan . --diff origin/main

# Run a deep scan of the repository.
cs scan . --mode deep

Use cs scan . --max-time 15 for an advisory 15-minute Standard investigation allowance. See investigation time for timing semantics and Deep Scan limits.

Use cs --help to browse commands, or cs scan --help for scan options, cost limits, and patching after a scan.

Investigate findings and generate patches

Use an issue number from the scan summary to view a finding, request a patch, or verify a fix:

bash
# View finding details and evidence.
cs finding show 1

# Generate and test a fix.
cs finding patch 1

# Verify a fix you wrote yourself.
cs finding verify 1

Generate a security policy

Draft or update SECURITY.md to guide future scans:

bash
# Draft a policy from repository analysis.
cs policy generate

# Update the existing policy with new questions or changed context.
cs policy update

The command checks for a policy file in your workspace, creates or updates one from source analysis, and shows what changed. Review and commit SECURITY.md so future scans use it automatically. If the command says the policy is already up to date, no copy is needed.

Save and export threat models

Scans and policy generation save threat models with their results. Export a saved model without starting another analysis:

bash
cs export --scan SCAN_ID --artifact threat-model --output threatmodel.md

Omit --scan to use the current repository's latest completed scan. The export guide also covers findings, SARIF output for CI, and the offline TypeScript API.

GitHub Actions

Run scheduled, manual, or pull request scans with the GitHub Action. For a weekly repository scan, add an OpenAI API key as the repository secret CODEX_SECURITY_API_KEY, then save this workflow in .github/workflows/codex-security.yml. Replace REPLACE_WITH_REVIEWED_COMMIT with the full SHA of an Action commit.

yaml
name: Codex Security
on:
  workflow_dispatch:
  schedule:
    - cron: "23 7 * * 1" # Mondays at 07:23 UTC

permissions:
  contents: read

jobs:
  security:
    runs-on: ubuntu-24.04
    steps:
      # Configure Bubblewrap and AppArmor so Codex Security can run safely in its sandbox.
      - name: Set up the Ubuntu sandbox
        run: |
          sudo apt-get update
          sudo apt-get install --yes bubblewrap apparmor-profiles
          sudo apparmor_parser -r /usr/share/apparmor/extra-profiles/bwrap-userns-restrict
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          persist-credentials: false
      - uses: openai/codex-security@REPLACE_WITH_REVIEWED_COMMIT
        with:
          model: gpt-5.6-sol
          effort: high
          cyber-access-program: daybreak_blue
        env:
          OPENAI_API_KEY: ${ secrets.CODEX_SECURITY_API_KEY }

Findings are report-only by default. Set a severity threshold to fail on reported findings at or above it. Scanner and required reporting errors fail the job; intentional file exclusions and investigation notes do not.

Containerized bulk scans

Scan a list of repositories with the included Docker Compose configuration, which keeps results and authentication between runs. See the container quick start. The workflow runner runs individual CLI stages in containers and can connect to a separately deployed findings service.

Findings storage and deduplication

The findings guide covers local storage, deduplication, and compatibility with independently operated endpoints through publish scan --to custom and explicit --findings-url. The local serve command and browser dashboard have been removed; existing databases and scan artifacts remain available.

Other providers

Scans support OpenAI, Amazon Bedrock, OpenRouter, Fireworks AI, and Cheaper Inference. Bedrock uses AWS credentials and does not require a separate OpenAI login. See Bedrock setup for AWS profiles, regions, and model access.

Documentation

📦 Full-Text Markdown Snapshot archived by Phying News · Original source: github.com/openai/codex-security

Related coverage

tool · github.com
Apple Private Cloud Compute (PCC) Security Source Code and Research Tools
Provides unprecedented source-level visibility into Apple's cloud AI infrastructure, allowing security researchers to verify cryptographic privacy guarantees and audit components eligible for Apple's PCC Security Bounty.
blog · about.gitlab.com
When your backlog outgrows your team, GitLab scales remediation
This coverage gives security teams current context for monitoring, validation, and remediation.
blog · aikido.dev
From Hugging Face to Fable: this summer shows AI control matters more than trust
This coverage gives security teams current context for monitoring, validation, and remediation.
tool · github.com
Brotli Client Checker: Test Server for Brotli Decoder Vulnerability (CVE-2026-111497)
Provides security teams and developers with a simple, zero-dependency mechanism to test whether backend microservices, crawlers, and HTTP clients are susceptible to the widespread Node2Shell/HTTP2Shell Brotli decoder flaw.
tool · github.com
node2shell-scanner: High-Fidelity Remote Detection Tool for Node.js Brotli OOB Write (CVE-2026-111497)
Provides defenders and security teams with a safe, non-destructive, and high-fidelity method to scan large attack surfaces and confirm Node.js exposure to the critical Brotli decoder flaw.
tool · github.com
Assetnote Releases php2shell-scanner: High-Fidelity Scanner for CVE-2026-109618 & CVE-2026-109619
As php2shell affects widespread PHP installations globally, this production-grade scanning logic enables enterprise security teams and defenders to reliably audit attack surfaces without relying on destructive exploit payloads.
Back