Claude Model Builds Exploits Across Major Browsers & OSes

Summary

Anthropic says an unreleased version of its AI model found and chained multiple vulnerabilities in Chrome, Safari, Android, Windows, and Linux. The source text gives no further detail on the flaws, versions or impact.

Related items

• InfoAPI credits benefit for eligible ChatGPT subscriptionsSame vendor · Simon Willison's Weblog
• LowAnthropic-Themed Phishing Emails Bypass Top Security ToolsSame vendor · Dark Reading
• InfoYou can generate and edit Google Docs files directly in Gemini chats nowSame vendor · The Verge (AI)
• InfoEndor Labs + Google Antigravity: Secure code by default in agentic workflows | Endor LabsSame vendor · Endor Labs Blog
• InfoBuilding a multiplayer game world with autonomous Fable-class modelsSame vendor · Simon Willison's Weblog