Anthropic Launches Claude Security in Public Beta, Using AI to Catch Complex Code Vulnerabilities Traditional Tools Miss

Anthropic launches Claude Security in public beta, an AI-powered tool that reasons through codebases like a skilled security researcher to catch complex vulnerabilities traditional pattern-matching tools miss, complete with adversarial self-verification to reduce false positives and human-reviewed patch suggestions.

• Claude Security, now in public beta for Enterprise customers, scans codebases, validates findings, and suggests patches by reasoning through code like a skilled security researcher to catch complex vulnerabilities that traditional pattern-matching tools miss.
• Every finding undergoes an adversarial self-verification pass to reduce false positives, and each flagged issue comes with a recommended patch that human teams must review and approve before any fix is applied.
• Claude Security integrates with existing workflows by pushing findings via webhooks to tools like Slack and Jira, supports scheduled and scoped scans, and is powered by the same models Anthropic uses to secure its own codebase.