AI Wiki · Mediocre Security
IncidentIncidents

Anthropic red team's AI-built exploit chains

An unreleased Anthropic model found and chained flaws in Chrome, Safari, Android, Windows and Linux; Google alone patched 62 CVEs.

What happened

Anthropic’s Frontier Red Team used an unreleased internal model to find and chain flaws in Chrome, Safari, Android, Windows and Linux into proof-of-concept exploits (Chrome chain: four flaws, sandbox escape from one page load; Google patched 62 CVEs including 13 sandbox escapes). All flaws were reported to vendors and are patched.

Timeline

Every dated event in the wiki that involves Anthropic red team's AI-built exploit chains, newest first.

Connections

Anthropic red team's AI-built exploit chains and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

AI lab Anthropic

Model family Claude

Company Google

Sources

  1. Anthropic, “Discovering and exploiting vulnerabilities in critical, real-world software with Claude”, Oct 27 2026