Microsoft Expands Sentinel Into Agentic Security Platform With Unified Data Lake
Summary: Microsoft announced the general availability of its Sentinel data lake and expanded Sentinel into a unified agentic SIEM platform, alongside public previews of Sentinel Graph and a Sentinel Model Context Protocol server that turn telemetry into a security graph and give AI agents standardized access to an organization's security context. Microsoft's Vasu Jakkal said the platform combines graph-based context, semantic access, and agentic orchestration so defenders can ingest signals, correlate across domains, and run AI agents built in Security Copilot, VS Code with GitHub Copilot, or other developer platforms.
What you should know: Microsoft is handing AI agents standardized access to your security context through an MCP server, which means the same platform now depends on defenses against prompt injection - threat protection in Defender for Cloud, Spotlighting in Azure AI Content Safety, and an AI Red Teaming Agent built on PyRIT - to keep those agents from acting on malicious inputs.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026