Xbow spent $40K on AI and cracked Google Chrome wide open

Xbow USA researchers spent $40,000 in AI compute time and six days to build a full-chain Chrome exploit that chained a V8 JavaScript engine sandbox escape with a Chrome OS-process sandbox escape, launching a Windows app from a malicious web page and earning a $250,000 Google bug bounty, the first under Google's 2026 patch rewards rules. The team used OpenAI's GPT-5.6 Sol to search Chrome's source code, test ideas and build proofs of concept while setting strategy and verifying its work, then reported the flaws to Google, which fixed them.

A chain of vulnerabilities in Google’s Chrome browser could have enabled researchers to take control of one billion Windows machines worldwide — and it cost them just $40,000 in AI compute time to discover it. Researchers at Xbow USA worked for six days on developing the exploit https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit , which earned them a $250,000 bug bounty from Google, the first under the new 2026 rules https://bughunters.google.com/about/rules/open-source/patch-rewards-program-rules? gl=1 apmt6y up MQ.. ga MjI3MjM3ODk1LjE3OTIxNTUxMTA. ga P3DR9DKB0P czE3OTIxNTUxMDkkbzEkZzAkdDE3OTIxNTUxMDkkajYwJGwwJGgw . They chose OpenAI’s GPT-5.6 Sol for the task to demonstrate what’s possible with a publicly available model rather than a specialist security implementation. They used it to search Chrome’s source code, test ideas, and build proofs of concept, while they set the strategy, chose where to look, and checked its work. They successfully chained together a vulnerability to escape first from the sandbox containing the V8 JavaScript engine and then from Chrome’s operating-system process sandbox, launching a Windows app from within a malicious web page. Xbow presented its findings to Google, which fixed the flaws. The researchers set out all the details as to how the exploit was developed in a blog https://xbow.com/labs/research/zero-to-calc-in-six-days-inside-xbow-chrome-full-chain .