Anthropic says an unreleased internal model built five exploit chains against Chrome, Safari and more; Chrome has patched 62 CVEs

Wed, Oct 28 02:15 UTC+8

Anthropic's Frontier Red Team wrote on Oct 27 that it used an unreleased internal research model to find bugs and build five attack chains against Chrome, Safari, Android, Windows and Linux, reaching remote code execution and other critical impacts with little or no user interaction. It says Google has assigned and patched 62 Chrome CVEs, all critical or high severity.

Why it matters

It suggests frontier models can now chain multiple bugs into working full exploits with little human help, once a niche specialist skill; Anthropic urges defenders to scan code at PR time and has released a Claude Code plugin for it.

Sources1

AnthropicOfficial · WebsiteWed, Oct 28 02:15 UTC+8Discovering and exploiting vulnerabilities in critical, real-world software with ClaudeView original · Wed, Oct 28 02:15 UTC+8

Written by dalao.ai: the title, summary and why it matters are our own words. The original reports are the record; their publishers keep authorship.