Skip to content
ATAI Today Brief
HomeNewsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Tools & releases/
  4. OpenAI Releases Codex Security CLI Tool and TypeScript SDK for Repository Audits
Tools & releases

OpenAI Releases Codex Security CLI Tool and TypeScript SDK for Repository Audits

July 29, 2026· 3 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated July 29, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
OpenAI Releases Codex Security CLI Tool and TypeScript SDK for Repository Audits

OpenAI released `@openai/codex-security`, a command-line tool and TypeScript SDK designed to scan codebases, track security findings, and integrate automated security reviews into Continuous Integration pipelines.

Impact: Medium

Why it matters

You can now embed automated OpenAI-powered code vulnerability scanning into local terminal workflows and continuous integration environments.

TL;DR

  • 01OpenAI releases @openai/codex-security for CLI and programmatic security scanning.
  • 02Requires Node.js 22+ and Python 3.10+ environments.
  • 03Supports both interactive ChatGPT logins and automated CI API keys.

Key facts

Minimum Node.js Versionv22.0.0
Minimum Python Versionv3.10.0
NPM Package
@openai/codex-security
Minimum Node.js Version
v22.0.0
Minimum Python Version
v3.10.0

Running Repository Scans via CLI

Execute scans using Node.js 22+ and Python 3.10+. Select explicit authentication sources based on execution context:

# Interactive execution with ChatGPT authentication
npx codex-security scan . --auth chatgpt

# CI execution with API key
export OPENAI_API_KEY="your-api-key"
npx codex-security scan . --auth api-key

Programmatic Usage with TypeScript SDK

Import and run scans within custom developer tools or build scripts:

import { CodexSecurity } from "@openai/codex-security";

const security = new CodexSecurity();
const result = await security.run(".");

State storage paths can be customized by setting CODEX_SECURITY_STATE_DIR to ensure write permissions inside restricted CI containers.

Try it in 2 minutes

import { CodexSecurity } from "@openai/codex-security";

const security = new CodexSecurity();
const result = await security.run(".");

typescript

✓ When to use

  • Use to perform automated vulnerability checks and security reviews on pull requests and local branches.

✕ When NOT to use

  • Do not run in public CI pipelines without isolating or restricting access to the underlying API keys.

What to do today

  • →Run npx @openai/codex-security scan . on your core repository to evaluate baseline security output.
  • →Add OPENAI_API_KEY to your GitHub Actions secrets to enable automated CI scan steps.

What the community says

  • “It's cool but must be very annoying to use without being allowed into the cybersecurity program.”

    — 0x_rs on Hacker News

#Codex Security#OpenAI#Node.js#Python#TypeScript

Sources

  • Codex Security Repository
ShareShare on XShare on LinkedIn
← Previous storyLiquid AI Releases LFM2.5 Encoders for Fast 8K Context CPU InferenceNext story →Anthropic Claude Mythos Preview Discovers Cryptographic Flaws and Launches CryptanalysisBench

Related stories

  • Tools & releasesEvaluating Frontier Model Usability: Grok 4.5 Efficiency vs Claude Fable 5 Reasoning
  • Tools & releasesGrafana Open-Sources Go LLM SDK Compatible with Vercel AI SDK React Hooks
  • Tools & releasesi-have-adhd Plugin Strips AI Assistant Fluff for Direct Code Action
  • Tools & releasesMicrosoft Announces MAI-Cyber-1-Flash Cybersecurity Model and Perception Agent System

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.