Anthropic's Claude Security now scans continuously, tracks fixes, with $25K/month credits
Claude (Anthropic) · rss · 2026-10-21
Anthropic announced a major Claude Security update: it now continuously monitors repositories as code changes, tracks findings until fixed, learns from team-provided context, and integrates with existing tools via API and MCP. Available in public beta for Claude Enterprise customers, with $25,000 in free monthly usage credits for two months (through Dec 31, 2026).
Key capabilities:
- Continuous monitoring: connect repos via the Claude GitHub app (incl. Enterprise Server) or GitLab tokens; a deep baseline scan is followed by regular risk-based scans. Projects can hold multiple repos to catch cross-service issues.
- Fix tracking: findings are marked fixed when the fix lands, and reopen automatically if the issue reappears.
- Team knowledge base: describe deployments and security policies; Claude generates an editable threat model that subsequent scans use to prioritize what to flag.
- Every finding includes a severity rating judged against the threat model, plus attacker exploit paths and diagrams.
- API + MCP integration: webhooks for new findings, resolve/reopen via API, fix findings directly in Claude.ai or Claude Code, and new role-based access controls.
Since April's beta, thousands of organizations have found over a million vulnerabilities with it; customers including IonQ, Vanta, and Gusto report it caught logic flaws that traditional pen tests and other tools missed.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23