Microsoft says its new multi-model agentic security system found 16 Windows vulnerabilities
Microsoft’s Security Blog describes MDASH, a harness orchestrating 100+ AI agents across multiple models to discover and prove exploitable bugs.
Microsoft says its new multi-model agentic scanning harness (codename MDASH) helped researchers find 16 vulnerabilities across the Windows networking and authentication stack, including four Critical remote-code-execution flaws. The post argues that the durable advantage is the surrounding agentic system — not any single model — and says MDASH is already being used by Microsoft security engineering teams and tested with a small set of customers in a limited private preview.
Read the original reporting at Microsoft Security Blog.
