vulnerability
Anthropic's Unreleased AI Model Chains Flaws Into Working Chrome, Safari, Windows and Linux Exploits
HighCVSS 9.8EPSS 1%
Summary
Anthropic's internal AI model, Claude, discovered a series of security flaws in Chrome, Safari, Android, Windows, and Linux, and successfully chained them together to create working proof-of-concept exploits. The model's ability to find and combine flaws was achieved with minimal human involvement, and the company proactively reported all identified flaws to vendors.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data