Continuous Scanning and Fix Tracking in Claude Security

Claude Security now re-scans your code repositories as changes land and tracks each finding until it's fixed, in public beta for Claude Enterprise customers.

Details

Connect repositories once through the Claude GitHub app, GitHub Enterprise Server, or a GitLab or other Git access token. Claude runs a first full scan, then re-scans changes based on their risk and complexity
Checks open findings against changed code and marks them fixed when a fix lands, whether the fix was made in Claude Code or elsewhere. A finding reopens automatically if the issue comes back
Each project has a knowledge base where teams describe how they deploy and which security policies apply. Claude builds an editable threat model from the code and uses it to rate severity and skip risks already handled
Each finding explains how an attacker could reach the vulnerable code, with an optional diagram of the attack path
An API, alerts to other systems when a new finding appears, and a connector for Claude.ai and Claude Code let teams pull findings into their existing tools
Admins turn it on in the admin console. Organizations get $25,000 in free usage credits per month for two months, for usage through December 31, 2026

Best for

Keeping a current list of security issues in your codebase instead of relying on one-off audits.

When to use it

Your team ships code often and point-in-time security reviews go stale within weeks.

Who benefits

Security and engineering leads at companies on Claude Enterprise.

Staying informed is great. Staying ahead is better.

Pick a topic and leave with something you created.

Start for Free Bring to Your Team

Get new module drops and weekly AI strategy.

Details

Best for

When to use it

Who benefits

More from Anthropic

Staying informed is great. Staying ahead is better.