Anthropic's Claude Security automatically rescans repositories as code changes
Anthropic's Claude Security now continuously monitors repositories, automatically rescanning after code changes land, automatically closing the corresponding issues once patches go live, reopening them when vulnerabilities recur, and combining security team notes and an editable threat model to determine which vulnerabilities attackers can actually reach. Previously it was only an on-demand or scheduled scanner, and results went stale as soon as the code changed. Anthropic says that since April, thousands of organizations have discovered more than 1 million vulnerabilities; Claude Enterprise customers can get public beta access, plus two months of $25,000 per month in credits through December 31, 2026.
Why read this
AI score 66
The original text explains that Claude Security has shifted from on-demand scanning to continuously tracking code changes, which readers can use to judge how security review processes will change.
Topics
View original postClaude Security now keeps up with your code as it changes. Connect your repositories once. Claude runs a deep first scan, then re-scans as changes land, so findings stay close to the current state of your code. In public beta on Claude Enterprise. https://t.co/J5kPSEhWp3
View original
Claude Security now keeps up with your code as it changes. Connect your repositories once. Claude runs a deep first scan, then re-scans as changes land, so findings stay close to the current state of your code. In public beta on Claude Enterprise. https://t.co/J5kPSEhWp3
Body
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.