Anthropic says internal Claude model found exploitable flaws in five major platforms
Overview
Anthropic says an unreleased internal Claude research model found vulnerabilities in Chrome, Safari, Android, Windows and Linux and chained them into five working attack chains.
According to IThome's report, all flaws were disclosed to the vendors under coordinated disclosure and have been fixed.
Anthropic reports 62 high or critical CVEs from the Chrome work. It also says the Linux flaw CVE-2026-98432 gave root access in 53 minutes.
Written by AI from the articles below · updated Oct 29, 5:52 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- IThome · AINewsPickAnthropic says its internal Claude model found exploitable flaws in five major platforms
AIAnthropic says an unreleased internal Claude research model found vulnerabilities in Chrome, Safari, Android, Windows and Linux, chaining them into five working attack chains. All flaws were reported to vendors under coordinated disclosure and fixed. The Chrome work produced 62 high or critical CVEs, and the Linux flaw CVE-2026-98432 gave root access in 53 minutes.
Heat Trend
Not enough continuous observations to show a trend yet.