Claude Code Security: AI That Hunts Vulnerabilities Like a Human Researcher
Anthropic just launched Claude Code Security, a tool that scans codebases for vulnerabilities the way a human researcher would — reasoning about how components interact rather than just pattern-matching like traditional static analysis. Using Claude Opus 4.6, Anthropic's team has already found over 500 bugs in production open-source projects that went undetected for decades, and the tool is now available in limited preview for Enterprise and Team customers, with free access for open-source maintainers. As AI-powered attacks become a real threat, this is a clear bet that defenders need the same AI firepower — and need it first.