After an initial deep baseline scan, the service regularly scans repository changes based on their risk and complexity. A project can include multiple repositories, including repositories connected through the Claude GitHub app, GitHub Enterprise Server, or access tokens for GitLab and other Git providers.
Open findings are checked against changed code and marked fixed when a fix lands, including fixes made outside Claude tools. A finding reopens if the issue is detected again. Teams can add deployment and policy context to a project knowledge base, review and edit a generated threat model, and receive severity and attack-path information for findings.
The release also adds an API, webhooks, role-based access controls, and an MCP connector in Claude.ai and Claude Code. It is available in public beta to Claude Enterprise customers. Anthropic says organizations receive $25,000 in usage credits per month for two months, for usage through December 31, 2026. The source does not establish independent detection accuracy, false-positive rates, or how the service compares with other security scanners.