Claude Security keeps up with your code

What changed

A one-time security scan starts going stale with the next push. Claude Security, Anthropic’s code-scanning tool for Claude Enterprise, now keeps up with your repositories as they change, in public beta.

What it makes possible

• Set it up once: create a project, connect up to eight repositories through the Claude GitHub app or with an access token for GitLab and other Git providers, and pick the branch and scope. Claude runs a deep baseline scan, then scans changes regularly based on their risk and complexity.
• Fixes get noticed: open findings are marked fixed when the fix lands, even if the fix was made outside Claude, and reopen automatically if the issue shows up again.
• Teach it your setup: each project has a knowledge base and a threat model you can edit, so Claude can skip risks your environment already handles. Each finding gets a severity rating and an explanation of how an attacker could reach the code.
• Plug it into your tools: an API, webhooks for new findings and a connector for Claude and Claude Code, plus role-based access controls for who can view, triage or create projects.

A use example

Jake Meredith, who works on product security at Gusto, as quoted by Anthropic: “Claude Security scanned our code once to set a baseline. Now it keeps up as our code changes, and our team fixes issues right in Claude instead of switching to another tool.”

Getting started

Admins turn it on in the admin console and choose who can use it. Eligible Enterprise organizations get up to $25,000 in promotional usage credits a month for two months, for usage through Dec 31, 2026.