Executive Summary
XBOW researchers directed AI agents running OpenAI's GPT-5.6 Sol to chain three unknown Chrome bugs into a full-chain exploit that runs code on Windows when a user loads a web page, in six days; Google fixed the bugs and paid a $250,000 bounty.
What Happened
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 $
Affected Products
- Google Chrome
- OpenAI GPT-5.6 Sol
Vulnerability / Attack Technique
AI-assisted vulnerability discovery and exploit chaining
Technical Mechanism
Agents running a publicly available model were directed to find and chain three browser bugs into a drive-by remote code execution exploit on Windows.
AI Security Category
AI-assisted attack
Part of the AI-Assisted Attacks topic.
RealGround Analysis
The vulnerabilities are in Chrome, not in an AI system; the significance is how quickly public models helped build a full chain. RealGround analysis: patch windows for widely used software are shrinking as AI-assisted exploitation matures.
Recommended Controls
- Keep browsers on automatic updates and verify fleet versions
- Shorten patch timelines for critical client-side software
- Isolate browsing for high-risk users
Related RealGround Service
AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/10/researchers-used-public-openai-model-to.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-17.