Understand this story
Anthropic said that over the past few months it used an unreleased internal research model to find critical vulnerabilities in widely used software such as browsers and operating systems, and identified five attack chains that can execute code remotely or bypass the lock screen. Among them, the Chrome-related findings have been assigned and fixed 62 CVEs, all of which are critical or high severity, with 13 being sandbox escapes; issues in Safari, Android, Windows, and Linux have also been reported to Apple, Google, and Microsoft respectively and fixed or patched upstream. Anthropic also said it has released a Claude Code plugin that embeds security scanning into the development workflow.
AI-generated from public reports
Latest development · Report
Anthropic used Claude on Chrome, Safari, Android, Windows and…Developments
1 confirmed developments
Anthropic uses internal research model to discover five real software attack chains
Source:Anthropic：The Institute
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 27
Anthropic：The InstituteFirst-partySelected
Anthropic used Claude on Chrome, Safari, Android, Windows and…
Anthropic said that over the past few months it used an unreleased internal research model to find critical vulnerabilities in widely used software such as browsers and operating systems, and presented five attack chains that can achieve remote code execution or bypass the lock screen. The Chrome-related findings have been assigned and fixed 62 CVEs, all of which are critical or high severity, 13 of which are sandbox escapes; the Safari, Android, Windows and Linux issues have also been reported to Apple, Google and Microsoft respectively and fixed or patched upstream. Anthropic also said it has publicly released a Claude Code plugin that embeds security scanning into the development workflow.