Anthropic's unreleased AI model chains flaws into working Chrome, Safari, Windows and Linux exploits

Anthropic said an unreleased AI model found vulnerabilities in Chrome, Safari, Android, Windows and Linux and chained them into working proof-of-concept exploits. The exploits were built in the lab on prompt, not seen in real attacks, and every flaw was reported to vendors and is already patched.

• Model found flaws in Chrome, Safari, Android, Windows and Linux
• The flaws were chained into working exploit proofs of concept
• Exploits were built in the lab, not seen in real attacks
• All vulnerabilities are already patched after vendor reports