Claude Security 升级：随代码变更持续扫描并自动关闭已修复漏洞
Anthropic 给 Claude Security 加了持续扫描：代码一改动就重扫，补丁合入自动关掉漏洞记录，企业管理版还有额度补贴。
Anthropic 更新 Claude Security，从按需扫描改为持续监控仓库，代码每次变更都会重新扫描。补丁合入后系统自动关闭对应漏洞记录，若漏洞复发会重新打开，无需人工维护过期报告。安全团队的备注和可编辑威胁模型用于判断攻击者实际能否触达漏洞。Anthropic 称自 4 月以来已有数千家组织用它发现超过 100 万个漏洞，Claude Enterprise 客户可获公共 beta 加每月 2.5 万美元额度（共 2 个月，截至 2026 年 12 月 31 日）。
Anthropic’s Claude Security now rescans repositories as code changes and marks findings fixed once patches land.
Until now, Claude Security was a scanner you ran (on demand or on a schedule) that handed you a list of bugs, and that list went stale as soon as your code changed.
But now it watches your repositories all the time, rescans each change as it lands, closes a finding by itself once the fix ships (wherever it was made), reopens it if the bug comes back, and uses notes from your security staff plus an editable threat model to judge which bugs an attacker could actually reach.
Anthropic says thousands of organizations have found over 1M vulnerabilities since April.
Claude Enterprise customers get the public beta plus $25K monthly credits for 2 months through December 31, 2026.
