#Anthropic unveils Claude Code Security in limited preview

#Anthropic has introduced Claude Code Security, an AI-powered tool designed to detect subtle vulnerabilities in codebases, including business logic flaws that traditional scanners often miss.

In early testing, it flagged more than 500 previously undetected issues across open-source projects. The system uses a multi-stage verification process, assigns severity ratings, and proposes targeted patches, all routed through a human review dashboard.

The rollout marks a deeper push into AI-assisted security auditing for development teams.