Search: “OpenAI Codex”

50 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Vulnerability 53 AI industry 40 Exploit / PoC 27 AI safety & security 25 AI tools & infra 14 Malware 12 Model release 9 Threat actor 8 AI research 7 Ransomware 6 Industry 5 Data breach 4 Research 4 Tools 3

SeverityAll critical 54 high 30 medium 45 low 7 info 87

ZDI-26-648: (Pwn2Own) OpenAI Codex External Control of System or Configuration Setting Remote Code Execution Vulnerability

ZDI published a Pwn2Own advisory for CVE-2026-19590, enabling remote code execution in OpenAI's Codex agent via system or configuration control.

Zero Day Initiative advisory ZDI-26-648 documents an External Control of System or Configuration Setting vulnerability in OpenAI Codex, demonstrated at Pwn2Own. A remote attacker could achieve arbitrary code execution, with user interaction required such as opening malicious content. The flaw is tracked as CVE-2026-19590 with a CVSS rating of 7.8. No exploitation in the wild is reported.

ZDI Published AdvisoriesSep 10, 05:00 UTC · 6d agoVulnerability 4 sources CVE-2026-195901

OpenAI Codex Security Scanned 1.2 Million Commits and Found 10,561 High

The Hacker NewsMar 7, 16:28 UTC · Mar 7, 2026Vulnerability CVE-2026-24881 CVE-2026-24882 CVE-2025-32988+10 CVEs

A $1,400 experiment in AI security auditing outperformed OpenAI's Codex Security

Help Net SecurityJun 23, 00:00 UTC · Jun 23, 2026Vulnerability

Pwn2Own Berlin 2026, Day Three: DEVCORE Crowned Master of Pwn, $1.298 Million Total

Security AffairsMay 17, 00:41 UTC · May 17, 2026Vulnerability

OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerability

The Hacker NewsMar 30, 18:05 UTC · Mar 30, 2026Vulnerability

Week in review: Notepad++ supply chain attack details and targets, Patch Tuesday forecast

Help Net SecurityFeb 8, 00:00 UTC · Feb 8, 2026Vulnerability in the wildCVE-2026-21509 CVE-2025-22225 CVE-2026-24423

OpenAI’s Daybreak uses Codex Security to identify risky attack paths

Help Net SecurityMay 12, 00:00 UTC · May 12, 2026Vulnerability

OpenAI wants AI to fix vulnerabilities, not just find them

Help Net SecurityJun 23, 00:00 UTC · Jun 23, 2026Vulnerability

Apple Patches 30+ iOS, macOS, Safari Flaws, Including AI

The Hacker NewsJun 30, 11:32 UTC · Jun 30, 2026Vulnerability in the wildCVE-2026-43707 CVE-2026-43716 CVE-2026-43745+6 CVEs1

New Attacks Trick OpenClaw AI Agent Into Running Code and Leaking Secrets

The Hacker NewsJun 11, 17:57 UTC · Jun 11, 2026Vulnerability

OpenAI Unveils Aardvark: GPT-5 Agent That Finds and Fixes Code Flaws Automatically

The Hacker NewsOct 31, 17:19 UTC · Oct 31, 2025Vulnerability

Ruflo MCP Flaw Lets Unauthenticated Attackers Run Commands and Poison AI Memory

The Hacker NewsJul 29, 15:39 UTC · Jul 29, 2026Vulnerability CVE-2026-597261

Attackers Exploit SimpleHelp CVE-2026-48558 to Deploy TaskWeaver and Djinn Stealer

The Hacker NewsJun 30, 11:18 UTC · Jun 30, 2026Vulnerability in the wildCVE-2026-485582

AI coding agents keep repeating decade-old security mistakes

Help Net SecurityJun 19, 12:07 UTC · Jun 19, 2026Vulnerability

New HTTP/2 Bomb Vulnerability Allows Remote DoS on NGINX, Apache, IIS, Envoy & Cloudflare

The Hacker NewsJun 10, 14:36 UTC · Jun 10, 2026Vulnerability CVE-2016-6581 CVE-2025-53020 CVE-2016-8740+3 CVEs

Microsoft responds to security challenges facing code, AI agents, and models

Help Net SecurityJun 3, 00:00 UTC · Jun 3, 2026Vulnerability1

Researcher Uncovers 30+ Flaws in AI Coding Tools Enabling Data Theft and RCE Attacks

The Hacker NewsDec 15, 00:00 UTC · Dec 15, 2025Vulnerability CVE-2025-49150 CVE-2025-53097 CVE-2025-58335+8 CVEs1

Secure Vibe Coding: The Complete New Guide

The Hacker NewsJun 19, 11:25 UTC · Jun 19, 2025Vulnerability

Week in review: Cisco patches SD-WAN 0-day, unpatched Microsoft Exchange Server flaw exploited

Help Net SecurityMay 17, 00:00 UTC · May 17, 2026Vulnerability in the wildCVE-2026-44413 CVE-2026-41940 CVE-2026-46300+2 CVEs1

OpenAI Expands Daybreak to Help Defenders Patch Flaws

Infosecurity MagazineJun 23, 14:15 UTC · Jun 23, 2026Vulnerability

Apple Fixes WebKit Flaws in iOS and macOS, With Help From AI Tools

Security AffairsJun 30, 11:32 UTC · Jun 30, 2026Vulnerability CVE-2026-43707 CVE-2026-43716 CVE-2026-43745+1 CVEs

Week in review: 74k Fortinet firewall credentials stolen, Splunk Enterprise RCE under active attack

Help Net SecurityJun 21, 00:00 UTC · Jun 21, 2026Vulnerability in the wildCVE-2026-20262 CVE-2026-48558 CVE-2026-39813+3 CVEs1

Chrome 153 Fixes 230 Vulnerabilities, Including One 0-Day Exploited in the Wild

Google shipped Chrome 153 with 230 fixes, including CVE-2026-87491, a V8 out-of-bounds write zero-day exploited in the wild.

Chrome 153 (153.0.8010.36/.37) rolls out to Windows, Mac, and Linux with 230 security fixes, among the largest patch batches in recent Chrome history. The headline flaw is CVE-2026-87491, a Medium-severity out-of-bounds write in the V8 JavaScript and WebAssembly engine that Google confirmed is exploited in the wild; it was reported by Jihyeon Jeong of Compsec Lab at Seoul National University for a $2,500 bounty. The release also closes five Critical-rated flaws, including CVE-2026-87464, CVE-2026-87488, CVE-2026-87438, CVE-2026-87527, and CVE-2026-87628, mostly use-after-free and out-of-bounds write bugs in WebGL and Cast, plus 43 High-severity issues across ANGLE, PDFium, V8, DevTools, and Payments. Several bugs were surfaced with AI-assisted discovery tools, including OpenAI's Codex Security team, and top bounties reached $5,000 for CVE-2026-87504.

Cyber Security NewsSep 9, 04:46 UTC · 7d agoVulnerability in the wildCVE-2026-87491 CVE-2026-87464 CVE-2026-87488+7 CVEs1