Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday
Vulnerabilities mentionedAll →
| CVE | Vulnerability | CVSS | EPSS | Flags | Affected | Exposure | Published |
|---|---|---|---|---|---|---|---|
| CVE-2026-33824 | Unauthenticated Double-Free RCE in Microsoft Windows IKE Extension A double-free memory-corruption flaw (CWE-415) in the Microsoft Windows Internet Key Exchange (IKE) service extension allows a remote, unauthenticated attacker to trigger the bug with crafted network traffic, with no privileges or user interaction required. Successful exploitation yields remote code execution with full system impact, reflected in the critical 9.8 CVSS score (high confidentiality, integrity, and availability). The vulnerable IKE component is present in Windows 10 (1607, 1809, 21H2, 22H2), Windows 11 (23H2, 24H2, 25H2, 26H1), and Windows Server 2016, 2019, and 2022 (including 23H2), which ship it as a built-in feature. CISA added the flaw to the Known Exploited Vulnerabilities catalog on 2026-08-18, and security reporting confirms it is being actively exploited in the wild, though ransomware use is not yet confirmed. No public proof-of-concept is known, but the high EPSS score (72.7%, 99th percentile) signals a very strong likelihood of imminent or ongoing exploitation. Do: Apply Microsoft's security updates for CVE-2026-33824 to all affected Windows 10, Windows 11, and Windows Server releases, prioritizing internet-exposed systems where IKE/VPN is reachable (UDP 500/4500), per BOD 26-04 requirements. Organizations unable to patch promptly should restrict or discontinue use of exposed IKE/VPN services on affected hosts until updated. Triage VPN endpoints and remote-access servers for crashes or suspicious IKE traffic given confirmed in-the-wild exploitation. | 9.8 | 73% | KEV |
| masswell over 1B Windows devices include the built-in IKE extension; internet-exposed VPN/IKE endpoints plausibly number in the hundreds of thousands | |
| CVE-2026-33827 | Concurrent execution using shared resource with improper synchronization ('race condition') in Windows TCP/IP allows an unauthorized attacker to execute code ov Concurrent execution using shared resource with improper synchronization ('race condition') in Windows TCP/IP allows an unauthorized attacker to execute code over a network. NVD description · AI analysis pending | 8.1 | <1% |
| — |
Full article535 words · extracted from thehackernews.com · click to collapse
Ravie LakshmananMay 13, 2026Vulnerability / Artificial Intelligence
Microsoft has unveiled a new multi-model artificial intelligence (AI)-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview.
MDASH, short for multi-model agentic scanning harness, is designed as a model-agnostic system that uses bespoke AI agents for different vulnerability classes to autonomously discover, validate, and prove exploitable defects in complex codebases like Windows.
"Unlike single-model approaches, the harness orchestrates more than 100 specialized AI agents across an ensemble of frontier and distilled models to discover, debate, and prove exploitable bugs end-to-end," Taesoo Kim, vice president of agentic security at Microsoft, said.
MDASH is envisioned as a "structured pipeline" that ingests a codebase and produces validated, proven findings through a series of actions.
It starts with analyzing the source code to build a threat model and attack surface, running specialized "auditor" agents over candidate code paths to flag potential issues, running a second set of "debater" agents that validate the findings, grouping semantically equivalent findings, and then finally proving the existence of the vulnerabilities.
The system is powered by a configurable panel of models, with state-of-the-art (SOTA) models used for reasoning, distilled models for validation for high-volume passes, and a second separate SOTA model for independent counterpoint.
"Disagreement between models is itself a signal: when an auditor flags something as suspect and the debater can't refute it, that finding’s posterior credibility goes up," Microsoft explained. "An auditor does not reason like a debater, which does not reason like a prover. Each pipeline stage has its own role, prompt regime, tools, and stop criteria."
Redmond noted that the specialized agents have been constructed based on past common vulnerabilities and exposures (CVEs) and their patches. It also said the architecture allows for portability across model generations.
MDASH has already been put to test, unearthing 16 of the vulnerabilities that were fixed in this month's Patch Tuesday release. The shortcomings span across the Windows networking and authentication stack, including two critical flaws that could pave the way for remote code execution -
- CVE-2026-33824 (CVSS score: 9.8) - A double-free vulnerability in "ikeext.dll" that could allow an unauthenticated attacker to send specially crafted packets to a Windows machine with Internet Key Exchange (IKE) version 2 enabled, leading to remote code execution.
- CVE-2026-33827 (CVSS score: 8.1) - A race condition vulnerability in Windows TCP/IP ("tcpip.sys") that allows an unauthorized attacker to send a specially crafted IPv6 packet to a Windows node where IPSec is enabled, leading to remote code execution exploitation.
News of MDASH follows the debut of Anthropic's Project Glasswing and OpenAI Daybreak, both of which are AI-powered cybersecurity initiatives for accelerating vulnerability discovery, validation, and remediation before they can be discovered by bad actors.
"The strategic implication is clear: AI vulnerability discovery has crossed from research curiosity into production-grade defense at enterprise scale, and the durable advantage lies in the agentic system around the model rather than any single model itself," Kim said.
Found this article interesting? Follow us on Google News, Twitter and LinkedIn to read more exclusive content we post.
Text extracted automatically; images, tables and formatting may be missing. Original: https://thehackernews.com/2026/05/microsofts-mdash-ai-system-finds-16.html