Claude Security Adds Continuous Repo Rescanning, Auto-Closes Fixed Findings

Claude Security, Anthropic's vulnerability scanning product, now rescans connected repositories continuously as new commits land and automatically closes findings when patches ship, reopening them if the same vulnerability reappears. The continuous monitoring feature is available in public beta for Claude Enterprise customers. Users connect a repository once; Claude runs an initial deep scan and then rescans on each commit, so findings reflect the current codebase state. The system also incorporates notes from security staff and an editable threat model to assess whether vulnerabilities are actually reachable by attackers. Anthropic reports thousands of organizations have found over one million vulnerabilities through Claude Security since April. The product originated as Claude Code Security, released February 20, 2026, as a limited research preview scanning codebases for vulnerabilities and recommending patches for human review. It moved to public beta for Claude Enterprise customers on April 30, 2026, with Team and Max tier access described as coming soon. Claude Enterprise customers in the public beta also receive $25,000 in monthly credits for two months through December 31, 2026.