XBOW Researchers Exploit Three Chrome Vulnerabilities Using OpenAI's GPT-5.6 Sol Model in Six-Day Development Cycle

Researchers at XBOW developed a full-chain exploit targeting Google Chrome by leveraging OpenAI's GPT-5.6 Sol model, chaining three previously unknown vulnerabilities to execute arbitrary code on Windows systems. Google confirmed the flaws, patched them, and awarded XBOW its highest reward for responsible disclosure.

A team at security firm XBOW chained three then-unknown Google Chrome bugs into a single attack that runs code on a Windows computer when the user only loads a web page, the company said.

Its researchers built the attack in six days by directing AI agents running OpenAI's publicly available GPT-5.6 Sol model. Google has since confirmed all three bugs, fixed them, and paid XBOW its top $

Read original article