Anthropic Launches AI-Powered Code Security Tool to Combat Vulnerability Overload

Anthropic launches Claude Code Security, an AI-powered tool that scans codebases by reasoning through component interactions like a human researcher, filtering false positives before human review — arriving at a critical moment as AI-driven coding surges and security teams struggle to keep pace with growing vulnerabilities.

• Anthropic launches Claude Code Security, an AI-powered tool now in limited research preview that scans codebases for vulnerabilities by reasoning through how components interact and data flows, mimicking the approach of a human security researcher rather than relying on traditional pattern-based scanning.
• All findings pass through a multi-stage false positive filtering process before appearing on a dashboard for human review and approval, directly addressing the growing problem of overwhelmed security teams facing too many vulnerabilities and too few skilled researchers.
• The release comes as developer reliance on AI coding tools surges, raising the stakes for failures — highlighted by a 13-hour AWS outage in December that reportedly involved an agentic AI coding tool — making trusted, secure codebases more critical than ever.