From the source
Anthropic is updating Claude Security so it scans repositories continuously and tracks which findings get fixed, rather than waiting for someone to start a scan.
- Since the tool entered public beta in April, thousands of organizations have used it to find over a million vulnerabilities, the company says.
- Each project now has a knowledge base where teams describe how their code is deployed and which policies apply, and Claude Security generates an editable threat model from the code that later scans use to decide what is worth flagging.
- Findings are marked fixed when the changed code shows the fix landed, and reopen automatically if the issue reappears.
- Every finding carries a severity rating judged against the project's threat model and an explanation of how an attacker could reach the vulnerable code, sometimes with an attack-path diagram.
- A new API lets teams list and read projects and findings, resolve or reopen them, and manage projects and repositories, with webhooks notifying systems when a finding lands; Claude Security is also available as an MCP connector in Claude.ai and Claude Code.
- The latest version is in public beta for Claude Enterprise customers, with admins enabling it in the admin console, and organizations receive $25,000 in free usage credits each month for two months, for usage through December 31, 2026.
