Microsoft Microsoft Launches MDASH AI Scanning for US Government Security
Article Content
- •Microsoft's MDASH AI scanning system launched for Azure Government on September 8, 2026.
- •The system uses over 100 specialized AI agents to find and validate vulnerabilities in source code.
- •MDASH aims to provide comprehensive coverage and prioritize vulnerabilities based on risk.
On September 8, 2026, Microsoft announced the deployment of its agentic AI scanning system, codename MDASH, to Azure Government. This system is designed to identify security flaws in software used by US government agencies and authorized partners. MDASH employs over 100 specialized AI agents to analyze source code, moving beyond traditional scanning methods that rely on known patterns. The system ranks files by risk and validates vulnerabilities through a multi-model debate process, aiming for comprehensive code coverage. Microsoft emphasizes that MDASH will help agencies proactively address subtle vulnerabilities that could be exploited by cyber adversaries. The deployment is currently in preview for select customers, with plans for broader access to follow. This initiative is part of Microsoft's ongoing commitment to enhance cybersecurity for critical government systems.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (4)
Following this threat?
Track Microsoft in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Continue Reading
Critical BeyondTrust 9.3 Vulnerability Actively Exploited by Threat Actor A critical vulnerability (CVE-2026-102764) in BeyondTrust Remote Support has been discovered and is actively being exploited by the threat group ARMORY CASTLE, reportedly linked to China. The vulnerability, which has a CVSS score of 9.3, allows unauthenticated attackers to upload files and potentially compromise host… 
Korean-speaking Hackers Target PHP Vulnerabilities in Global Campaign A cybersecurity report from Cyfirma reveals that attackers, possibly linked to North Korea's Lazarus group, are preparing to exploit critical vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619). These vulnerabilities allow unauthenticated remote code execution, posing a significant threat to government…