Claude Security now scans continuously and tracks fixes
- ID
- 37956
- Status
- summarized
- Published
- 21 Oct 2026, 8:00 AM
- Fetched
- 22 Oct 2026, 1:56 AM
- Provider
- Claude
- Category
- ai-labs
- Original URL
- https://claude.com/resources/articles/claude-security-now-scans-continuously-and-tracks-fixes
- Source URL
- https://raw.githubusercontent.com/leontloveless/ai-rss-feeds/main/feeds/claude.xml
Summary
- Score
- 5.5
- Created
- 22 Oct 2026, 1:56 AM
- Tags
- Audience
- developerssaas_founders
What happened
Anthropic's Claude Security moved from on-demand scans to continuous monitoring: you connect repos via the Claude GitHub app (including GitHub Enterprise Server) or a GitLab/other provider access token, pick branches and scope per project, and it runs a deep baseline scan then rescans changes based on risk and complexity. Findings are auto-marked fixed when the fix ships in code — even if fixed outside the tool — and reopen automatically if the issue reappears; each project also gets a knowledge base for deployment context and security policies, plus an editable generated threat model. It stays in public beta for Claude Enterprise customers, with $25,000 in free usage credits per month for two months on usage through December 31, 2026; Anthropic says thousands of organizations have found over a million vulnerabilities since the April beta.
Why it matters
The status field is the thing to scrutinise: 'fixed' now comes from diffing changed code, not from a human verifying the remediation, so a team on Claude Enterprise could report a cleaner backlog than it actually has unless someone spot-checks the reopen logic against their real fix workflow. Everyone else should note the gate — this is Claude Enterprise-only public beta, so indie teams and solo builders get no new capability from this announcement and shouldn't plan around it.
Discussion angle
Would you trust a scanner that closes its own findings based on a code diff? Worth walking through a case where the code changed but the vulnerability didn't actually go away, and what your team's review step should look like before trusting an auto-'fixed' status.