OpenAI launched Codex Security on Friday, an AI security agent that identifies and suggests fixes for vulnerabilities. The feature is in research preview for ChatGPT Pro, Enterprise, Business, and Edu customers through the Codex web, available free for the next month.
“It 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 said.
By infosecbulletin
/ Thursday , November 19 2026
A large cyberattack affected Windows-based POS machines, leading to the theft of over one million unique credit and debit card...
Read More
By infosecbulletin
/ Wednesday , November 18 2026
Bangladesh has achieved a significant milestone in the global cybersecurity landscape as Knight Squad Academy becomes the country's first organization...
Read More
By infosecbulletin
/ Wednesday , November 18 2026
Cyberattacks are rising around the world, including ransomware, malware, data leaks, and hacked websites. These events show how complex and...
Read More
By infosecbulletin
/ Wednesday , November 18 2026
The Fugaku supercomputer at Japan's RIKEN Center for Computational Science is now offline because of a security incident. The organization says...
Read More
By infosecbulletin
/ Tuesday , November 17 2026
A supply chain attack targeting Optimizely has led to malicious JavaScript being loaded on numerous popular websites, including Zoom, CNN,...
Read More
By infosecbulletin
/ Tuesday , November 17 2026
Cybersecurity researcher Jeremiah Fowler uncovered a massive database containing approximately 150 million images associated with the Kik messaging platform that...
Read More
By infosecbulletin
/ Monday , November 16 2026
Microsoft says a software bug introduced in July caused last week's worldwide Microsoft 365 outage, triggering a cascading failure that...
Read More
By infosecbulletin
/ Monday , November 16 2026
A new OWASP Incubator Project shows a missed area in AI security: servers, networks, and data centers for AI systems...
Read More
By infosecbulletin
/ Sunday , November 15 2026
Six remote code flaws were found in the Danfoss AK-SM800A supermarket fridge controller. These flaws let someone take control from...
Read More
By infosecbulletin
/ Saturday , November 14 2026
Cyberattacks are rising around the world, including ransomware, malware, data leaks, and hacked websites. These events show how complex and...
Read More
Codex Security is an improvement of Aardvark, launched by OpenAI in private beta in October 2025, designed for developers and security teams to identify and address security vulnerabilities effectively.
In the past 30 days, Codex Security has scanned over 1.2 million commits in external repositories during the beta phase, uncovering 792 critical and 10,561 high-severity vulnerabilities. These issues affect various open-source projects such as OpenSSH, GnuTLS, GOGS, Thorium, libssh, PHP, and Chromium. Here are some examples –
GnuPG – CVE-2026-24881, CVE-2026-24882
GnuTLS – CVE-2025-32988, CVE-2025-32989
GOGS – CVE-2025-64175, CVE-2026-25242
Thorium – CVE-2025-35430, CVE-2025-35431, CVE-2025-35432, CVE-2025-35433, CVE-2025-35434, CVE-2025-35435, CVE-2025-35436
The new version is easier to understand and focuses on clarity:
The AI company states that the latest version of the application security agent uses advanced models and automated checks to reduce false positives and provide clear solutions.
OpenAI’s scans of the same repositories over time have shown improved accuracy and reduced false positive rates, which have dropped by over 50%.
“OpenAI said Codex Security is designed to improve signal-to-noise by grounding vulnerability discovery in system context and validating findings before surfacing them to users” reported by thehackernews.