Anthropic Previews Claude Code Security for Vulnerability Scanning and Patching
Summary
Anthropic is rolling out Claude Code Security in a limited research preview for Enterprise and Team customers. It scans codebases, rates findings, verifies results, and proposes patches for human approval.
Key points
- Claude Code Security is available in a limited research preview to Enterprise and Team customers.
- Anthropic says the feature analyzes code and component interactions, traces data flows, and seeks vulnerabilities that rule-based tools may miss.
- Anthropic says findings undergo multi-stage verification and receive severity and confidence ratings.
- The feature suggests patches for analysts to review; changes require human approval.
- Anthropic presents the feature as a way to help defenders address vulnerabilities that AI-enabled attackers could discover.
Article Details
- Event Type
- Launch of an AI-powered code vulnerability scanning feature
- Impact
- Anthropic began a limited research preview of Claude Code Security for Enterprise and Team customers. It scans codebases for vulnerabilities, suggests targeted patches for human review, and provides severity and confidence ratings after multi-stage verification. Changes require human approval.
Vendors
Products
Claude CodeAnthropic has begun rolling out Claude Code Security, an AI-powered feature that scans codebases for vulnerabilities and suggests targeted patches for human review.Claude Code SecurityAnthropic has begun rolling out Claude Code Security, an AI-powered feature that scans codebases for vulnerabilities and suggests targeted patches for human review.