Xbow used $40,000 of AI compute to find a Chrome exploit chain, earning a $250,000 bounty from Google
Researchers at Xbow USA spent six days developing a Chrome exploit chain that first escaped the sandbox hosting the V8 JavaScript engine, then escaped Chrome's operating system process sandbox, allowing a Windows application to be launched from within a malicious webpage; Google has fixed the relevant flaws. They chose OpenAI's GPT-5.6 Sol to search Chrome source code, validate ideas, and build a proof of concept, while strategy formulation, search direction, and result verification remained the responsibility of the researchers. The AI compute cost $40,000, and they received a $250,000 bug bounty from Google, the first under the new 2026 rules.
Why read this
AI score 74
Xbow used public models to complete a Chrome exploit chain in six days, offering a way to observe the costs and division of labor when AI participates in security research.
Topics
Body
by Maxwell Cooter
Xbow spent $40K on AI and cracked Google Chrome wide open
Oct 16, 20262 mins
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, which earned them a $250,000 bug bounty from Google, the first under the new 2026 rules.
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.
VulnerabilitiesSecurityChromeBrowsersProductivity SoftwareBrowser SecurityEndpoint Protection
by Maxwell Cooter
Maxwell began writing about technology in 1984, when mainframes ruled the world. Since then he has written for just about every business computing title in the UK, and for a few in the US, covering everything from Artificial intelligence to Zero-day exploits and all points in between. He has also been editor-in-chief of several award-winning titles, including Network Week, Techworld, and Cloud Pro, and a regular contributor to Whatsonstage.com. In his spare time he coaches a junior rugby team.
More from this author
AI datacenter capex will far exceed forecast revenue through 2030 Oct 16, 2026 2 mins
AI bot company Character.ai seeks bankruptcy protection Oct 16, 2026 2 mins
Bidding war over key component could eliminate third hard disk maker Oct 9, 2026 2 mins
Ransomware consultant said he would decrypt data, is accused of paying ransoms instead Oct 9, 2026 3 mins
Google makes its most powerful AI models pay-for-play as AI services struggle to turn users into customers Oct 9, 2026 2 mins
Trump’s Super Intelligence edict supercharges .si domain registrations Oct 2, 2026 1 min
US FTC will investigate Anthropic and OpenAI Oct 2, 2026 2 mins
Show me more
opinion
October Patch Tuesday: 1,408 CVEs, 1 exploited flaw and a SharePoint surprise By Greg LambertOct 16, 202613 mins Microsoft OfficeMicrosoft SharePointWindows Security
news analysis
Apple’s big AI week ends with Mac + Muse AI supercomputers By Jonny EvansOct 16, 202610 mins AppleArtificial IntelligenceMac
Xbow spent $40K on AI and cracked Google Chrome wide open By Maxwell CooterOct 16, 20262 mins Browser SecurityBrowsersChrome
podcast
Can your tech stack actually handle AI? Aug 11, 202630 mins Artificial IntelligenceEnterprise ArchitectureGenerative AI
podcast
Microsoft Copilot Growth, ClaudeBleed Risk, LinkedIn GDPR Complaint | Ep. 84 By Arnold DavickMay 22, 20262 mins Artificial Intelligence
AI agents are starting to talk to each other. Here’s what could go wrong Oct 6, 202631 mins Artificial IntelligenceData and Information SecurityGenerative AI
AI slop is creating more work, not less. Here's why. Sep 22, 202631 mins Artificial IntelligenceGenerative AIIT Leadership
Why AI tools alone won't make your workforce more productive Sep 8, 202640 mins Artificial IntelligenceGenerative AIIT Skills and Training