Anthropic Launches Claude Code Security to Scan Codebases for Security Vulnerabilities
Anthropic has introduced Claude Code Security, a feature within Claude Code, designed to assist developers and security teams in identifying and mitigating vulnerabilities within codebases.
Anthropic has introduced Claude Code Security, a feature within Claude Code, designed to assist developers and security teams in identifying and mitigating vulnerabilities within codebases.
Claude Code Security is currently available in a limited research preview. The tool employs AI-powered code scanning that surpasses traditional static analysis by understanding the functional dynamics of code, rather than merely analyzing its content.
Conventional tools often depend on rule-based scans to identify known vulnerability patterns, such as hardcoded passwords or missing encryption. While effective, these methods may overlook complex or context-dependent flaws, including logic errors or insufficient access controls.
Claude Code Security employs a multi-layered verification process for identified vulnerabilities. This system re-evaluates its detections to reduce false positives and assigns severity and confidence ratings to each result. Findings appear on the Claude Code Security dashboard for review, where teams can assess suggested patches and approve final fixes.
Users maintain full control over remediation steps, aligning with the growing demand for automation in vulnerability management.
Security teams globally face significant backlogs as software vulnerabilities increase. Anthropic's introduction of Claude Code Security aims to alleviate this workload by supplementing human expertise with AI-driven insights, ensuring accuracy and accountability.
Feature Description
Claude Code Security is currently available in a limited research preview.
AI vulnerability detection Scans code for security issues and suggests fixes for review.
Context-aware analysis Understands data flow and component interactions to find complex flaws.
Multi-stage verification Rechecks findings to reduce false positives.
Severity ratings Assigns priority levels and confidence scores to issues.
Human review Developers review and approve suggested fixes.
Security dashboard Shows validated issues and tracks remediation progress.
Powered by Claude Opus 4.6 Uses the latest Claude model to detect serious vulnerabilities.
Defender-focused design Helps security teams manage growing vulnerability backlogs.
Anthropic's internal Frontier Red Team has rigorously tested these capabilities through various initiatives. With the assistance of Claude Opus 4.6, the AI has reportedly identified over 500 previously undetected vulnerabilities in open-source projects. As AI continues to evolve in cybersecurity, Claude Code Security is positioned as a tool for defenders to counter emerging threats effectively.
Enterprise and Team customers can now request early access to Claude Code Security, while open-source maintainers are invited to join a fast-tracked preview program.
Based on reporting by Cyber Security News.