• OpenAI unveils Codex Security for vulnerability detection
• Tool reduces false positives and triage workload
• Now in research preview, free for one month

OpenAI has released Codex Security, a new security agent which can surface high-impact software vulnerabilities while cutting down on time security teams must spend on triage.

Codex Security, an evolution of a tool previously known as Aardvark, "builds deep context about your project to identify complex vulnerabilities that other agentic tools miss, surfacing higher-confidence findings with fixes that meaningfully improve the security of your system while sparing you from the noise of insignificant bugs,” the company says.

It notes most AI security tools just flag low-impact findings and generate false positives, which force security teams to spend significant time on triage. At the same time, AI agents are speeding up software development, which turns security reviews into a major bottleneck.

Research preview

That’s why context is essential and, is hopefully where Codex shines.

“By combining agentic reasoning from our frontier models with automated validation, it delivers high-confidence findings and actionable fixes so teams can focus on the vulnerabilities that matter and ship secure code faster,” OpenAI concluded.

Previously only a private beta for a select group of customers, the tool has been improved by increasing precision, reducing the rate of findings with over-reported severity, and cutting down on false positives.

Now, the tool is emerging from private beta into research preview, available to ChatGPT Pro, Enterprise, Business, and Edu customers, via Codex web. It will be free to use for the next month, OpenAI said, suggesting that the tool will cost extra going forward.

There were no hints on how much it might cost after the free month period has passed, but it seems to be a direct competitor to Claude Opus 4.6.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!

And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.

Sead is a seasoned freelance journalist based in Sarajevo, Bosnia and Herzegovina. He writes about IT (cloud, IoT, 5G, VPN) and cybersecurity (ransomware, data breaches, laws and regulations). In his career, spanning more than a decade, he’s written for numerous media outlets, including Al Jazeera Balkans. He’s also held several modules on content writing for Represent Communications.