Claude Security goes continuous: scans code as it changes, has found 1M+ vulnerabilities
rohanpaul_ai · x · 2026-10-22
Anthropic announced a major update to Claude Security, now in public beta for Claude Enterprise customers. Since its April beta, thousands of organizations have used it to find over a million vulnerabilities.
Key capabilities:
- Continuous monitoring: connects repos via the Claude GitHub app (incl. GitHub Enterprise Server) or GitLab/Git access tokens, runs a deep baseline scan, then scans changes regularly based on risk and complexity
- Fix tracking: follows findings until they're resolved
- Context learning: uses team-provided context to prioritize what matters
- API and MCP integration, with multi-repo projects to catch cross-repo issues
It's powered by the full Claude model family, including Claude Mythos, with no Cyber Verification Program access required. Enterprise customers get $25,000 in free monthly credits for two months, applicable through December 31, 2026.
Related event: Claude Security Adds Continuous Scanning, Over 1M Bugs Found in Beta(4 posts)→
More from coding & agent
- Oblivion Remastered mod built with Claude AI boosts FPS by 37% and slashes stuttering — PikaPikaDude · 2026-10-22
- New paper proves linear convergence for LLM agent teams via block optimization — peter_richtarik · 2026-10-22
- Deterministic agentic compliance pipeline fails to escalate violation in 1 of 4 runs — ycombinator · 2026-10-22
- LangSmith Fine-Tuning Turns Agent Traces Into Models: 9B Beats Frontier on Task Benchmark — Hacubu · 2026-10-22
- MiniMax M3.1 Flash pairs with SGLang Omni for interruptible real-time voice agents — MiniMax_AI · 2026-10-22
- Routing strongest model every turn is bad design: one route per turn, pin through tools — WirelessLife · 2026-10-22