Anthropic has launched Claude Code Security, a new tool that scans codebases and suggests patches for detected security issues. Currently available in limited preview for Enterprise and Team clients, repository maintainers can request priority free access. Unlike traditional static analysis, Claude Code Security analyzes code like a human security researcher, detecting complex vulnerabilities such as business logic flaws and broken access controls.

The tool performs multi-step verification to reduce false positives, presenting findings in a dashboard with severity and confidence levels. No changes are made without human approval. Developed over a year with extensive testing, Claude Code Security has discovered over 500 unnoticed vulnerabilities in open-source projects.

Source: Anthropic