Claude Security Adds Continuous Repository Scanning

Anthropic detailed an update to Claude Security in a company blog post, adding continuous repository scanning, fix tracking, and project context. The updated service is available in public beta for Claude Enterprise customers. Anthropic says thousands of organizations have used Claude Security to find more than a million vulnerabilities since it entered public beta in April, and that it runs on its full model family, including Claude Mythos, without Cyber Verification Program access.

Teams can connect repositories through the Claude GitHub app or access tokens for GitLab and other providers. Claude Security runs a baseline scan, checks later code changes based on risk and complexity, marks findings as fixed when changes land, and reopens them if the issue returns.

Projects now include a knowledge base and an editable threat model that guide severity ratings and identify reachable attack paths. An API, webhooks, an MCP connector, and role based access controls connect findings with existing workflows. Enterprise customers receive $25,000 in monthly usage credits for two months, for usage through December 31, 2026.