CYBERSECURITYTRACKER
Permanent story citation

Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six Days

This page keeps the story as Cybersecurity Tracker first published it. If the tracker later corrects it, the correction appears below the original and never replaces it.

Back to newsStory 10242

As cited

Copy frozen at (site build).

vulnerabilities

Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six Days

Security researchers at XBOW combined three previously unknown Google Chrome vulnerabilities into a full-chain exploit that enables remote code execution on Windows systems through a malicious web page. The team built the attack in six days using artificial intelligence (AI) agents running OpenAI's GPT-5.6 Sol model. Google has confirmed all three bugs, released patches, and awarded XBOW its maximum bug bounty.

Why it matters: Windows users are affected by the complete exploitation chain that requires only visiting a malicious webpage; Chrome users and Google should prioritize applying patches immediately, and organizations should monitor for indicators of this attack pattern.

VendorsMicrosoftGoogle
Source published
First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

vulnerabilities

Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six Days

Security researchers at XBOW combined three previously unknown Google Chrome vulnerabilities into a full-chain exploit that enables remote code execution on Windows systems through a malicious web page. The team built the attack in six days using artificial intelligence (AI) agents running OpenAI's GPT-5.6 Sol model. Google has confirmed all three bugs, released patches, and awarded XBOW its maximum bug bounty.

Why it matters: Windows users are affected by the complete exploitation chain that requires only visiting a malicious webpage; Chrome users and Google should prioritize applying patches immediately, and organizations should monitor for indicators of this attack pattern.

VendorsGoogleMicrosoft
Source published
First seen by Cybersecurity Tracker

Source attribution

Correction

Correction recorded as of .

vulnerabilities

Researchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six Days

Security researchers at XBOW combined three previously unknown Google Chrome vulnerabilities into a full-chain exploit that enables remote code execution on Windows systems through a malicious web page. The team built the attack in six days using artificial intelligence (AI) agents running OpenAI's GPT-5.6 Sol model. Google has confirmed all three bugs, released patches, and awarded XBOW its maximum bug bounty.

Why it matters: Windows users are affected by the complete exploitation chain that requires only visiting a malicious webpage; Chrome users and Google should prioritize applying patches immediately, and organizations should monitor for indicators of this attack pattern.

VendorsAdobeAmazon Web ServicesCiscoGitHubGoogleMicrosoftSlack
Source published
First seen by Cybersecurity Tracker

Source attribution

Glossary