Anthropic has begun rolling out Claude Code Security, an AI-powered feature that scans codebases for vulnerabilities and suggests targeted patches for human review. Available in a limited research preview to Enterprise and Team customers, it uses human-like reasoning, multi-stage verification, severity and confidence ratings, and a human-in-the-loop workflow to help defenders counter AI-enabled attacks and avoid false positives. #Anthropic #ClaudeCodeSecurity
Keypoints
- Claude Code Security scans codebases and suggests targeted software patches for human review.
- The feature is in a limited research preview for Enterprise and Team customers.
- It reasons about code like a human researcher, tracing data flows and component interactions beyond static rules.
- Findings undergo multi-stage verification and receive severity and confidence ratings to reduce false positives.
- The system uses a human-in-the-loop approach and requires analyst approval before applying any changes.
Read More: https://thehackernews.com/2026/02/anthropic-launches-claude-code-security.html