Securing CI/CD in an agentic world: Claude Code Github action case

Microsoft Threat Intelligence discovered that Anthropic's Claude Code GitHub Action could expose CI/CD workflow secrets when AI agents process untrusted GitHub content, including issue bodies, pull request descriptions, and comments. We found that while Claude Code Action supported environment...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

Preinstall to persistence: Inside the Red Hat npm Miasma credential-stealing campaign

In this article 1. Attack chain overview 2. Mitigation and protection guidance 3. Learn more Microsoft Threat Intelligence identified a large-scale npm supply chain attack affecting 32 maliciously modified packages across more than 90 versions under the @redhat-cloud-services npm scope. The...

Microsoft Build 2026: Securing code, agents, and models across the development lifecycle

In this article 1. Secure your code 2. Secure your agents 3. Trust agents with your data 4. Secure your models 5. Trust starts with security Today, developers and security teams are caught in growing tension. AI is accelerating development and introducing new issues around insecure code, opaque...

Malicious npm packages abuse dependency confusion to profile developer environments

In this article 1. Attack chain overview 2. Threat actor attribution 3. Mitigation and protection guidance 4. Indicators of Compromise IOC 5. References 6. Learn more Microsoft Threat Intelligence has uncovered an active supply chain attack involving malicious npm packages registered under...

Microsoft is named a Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection

As threats become more coordinated and faster to execute, endpoint protection has become the proving ground for modern defense. For the seventh consecutive time, Microsoft has been named a Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection. We believe this reflects both the...

Typosquatted npm packages used to steal cloud and CI/CD secrets

In this article 1. Attack chain overview 1. The lure: typosquats and spoofed metadata 2. Execution: npm lifecycle hook abuse 3. Gen-1 stager: HTTP C2 beacon and payload drop 4. Gen-2 stager: abusing the legitimate Bun runtime as a loader 5. Credential theft 6. Impact and blast radius 2. Mitigatio...

Typosquatted npm packages used to steal cloud and CI/CD secrets

In this article 1. Attack chain overview 1. The lure: typosquats and spoofed metadata 2. Execution: npm lifecycle hook abuse 3. Gen-1 stager: HTTP C2 beacon and payload drop 4. Gen-2 stager: abusing the legitimate Bun runtime as a loader 5. Credential theft 6. Impact and blast radius 2. Mitigatio...

The Gentlemen ransomware: Dissecting a self-propagating Go encryptor

In this article 1. Pre-encryption 2. File encryption 3. Post-encryption 4. Defending against The Gentlemen ransomware 5. Microsoft Defender detections and hunting guidance 6. Indicators of compromise Ransomware that combines robust encryption with rapid lateral movement significantly increases th...

The Gentlemen ransomware: Dissecting a self-propagating Go encryptor

In this article 1. Pre-encryption 2. File encryption 3. Post-encryption 4. Defending against The Gentlemen ransomware 5. Microsoft Defender detections and hunting guidance 6. Indicators of compromise Ransomware that combines robust encryption with rapid lateral movement significantly increases th...

From poisoned search results to GPU mining: A cryptojacking campaign abusing ScreenConnect and Microsoft .NET utilities

In this article 1. Attack chain overview 2. Mitigation and protection guidance 3. References 4. Learn more Microsoft Defender Experts identified an active cryptojacking campaign in which malicious download sites are surfaced not only through traditional search engine poisoning, but also through A...

From poisoned search results to GPU mining: A cryptojacking campaign abusing ScreenConnect and Microsoft .NET utilities

In this article 1. Attack chain overview 2. Mitigation and protection guidance 3. References 4. Learn more Microsoft Defender Experts identified an active cryptojacking campaign in which malicious download sites are surfaced not only through traditional search engine poisoning, but also through A...

Microsoft recognized as a Leader in The Forrester Wave™ for Workforce Identity Security Platforms

Identity is the backbone of modern cybersecurity. Every access decision carries risk, across employees, partners, devices, workloads, and an expanding set of AI-powered agents. But most organizations are still operating across disparate systems. Identity signals are captured in one place, access...

From edge appliance to enterprise compromise: Multi-stage Linux intrusion via F5 and Confluence

In this article 1. Attack chain overview 1. Initial access: Exploiting edge appliances 2. Discovery and reconnaissance 3. Lateral movement and identity compromise 2. Mitigation and protection guidance 1. Microsoft Defender XDR detections 2. Advanced hunting 3. Indicators of compromise IOC 4. MITR...

From edge appliance to enterprise compromise: Multi-stage Linux intrusion via F5 and Confluence

In this article 1. Attack chain overview 1. Initial access: Exploiting edge appliances 2. Discovery and reconnaissance 3. Lateral movement and identity compromise 2. Mitigation and protection guidance 1. Microsoft Defender XDR detections 2. Advanced hunting 3. Indicators of compromise IOC 4. MITR...

Microsoft Security success stories: How St. Luke’s and ManpowerGroup are securing AI foundations

AI is reshaping how work gets done—and how risks emerge across cloud, data, identity, and more. Many organizations want AI-powered productivity, but their security foundations aren’t yet built for it. As organizations move toward AI-powered operating models, security becomes the critical enabler ...

Microsoft Security success stories: How St. Luke’s and ManpowerGroup are securing AI foundations

AI is reshaping how work gets done—and how risks emerge across cloud, data, identity, and more. Many organizations want AI-powered productivity, but their security foundations aren’t yet built for it. As organizations move toward AI-powered operating models, security becomes the critical enabler ...

What’s new in Microsoft Security: May 2026

At Microsoft, security innovations are purpose-built to help every organization protect end-to-end with the speed and scale of AI. Our vision is simple: security should be ambient and autonomous, just like the AI it protects. As organizations accelerate AI adoption, security teams are navigating...

What’s new in Microsoft Security: May 2026

At Microsoft, security innovations are purpose-built to help every organization protect end-to-end with the speed and scale of AI. Our vision is simple: security should be ambient and autonomous, just like the AI it protects. As organizations accelerate AI adoption, security teams are navigating...

Mini Shai Hulud: Compromised @antv npm packages enable CI/CD credential theft

In this article 1. Attack chain overview 1. Technical analysis 2. How GitHub took action to prevent further harm 2. Mitigation and protection guidance 1. Microsoft Defender XDR Detections 2. Microsoft Defender XDR Threat analytics 3. Advanced hunting 4. Indicators of Compromise IOC 3. References ...

Mini Shai Hulud: Compromised @antv npm packages enable CI/CD credential theft

In this article 1. Attack chain overview 1. Technical analysis 2. How GitHub took action to prevent further harm 2. Mitigation and protection guidance 1. Microsoft Defender XDR Detections 2. Microsoft Defender XDR Threat analytics 3. Advanced hunting 4. Indicators of Compromise IOC 3. References ...

Securing the gaming culture of cultures

The Deputy CISO blog series is where Microsoft Deputy Chief Information Security Officers CISOs share their thoughts on what is most important in their respective domains. In this series, you will get practical advice, tactics to start and stop deploying, forward-looking commentary on where the...

Introducing RAMPART and Clarity: Open source tools to bring safety into Agent development workflow

In this article 1. Why we are investing in this 2. RAMPART: Continuous safety testing for agentic AI 3. Clarity: Helping check software engineering assumptions 4. RAMPART and Clarity available now The AI systems shipping inside enterprises today are fundamentally different from the ones we were...

Exposing Fox Tempest: A malware-signing service operation

In this article 1. Fox Tempest’s role and impact 2. Fox Tempest’s malware signing as a service infrastructure 3. Defending against Fox Tempest-enabled attacks 4. Microsoft Defender detections 5. Indicators of compromise Fox Tempest is a financially motivated threat actor that operates a...

Exposing Fox Tempest: A malware-signing service operation

In this article 1. Fox Tempest’s role and impact 2. Fox Tempest’s malware signing as a service infrastructure 3. Defending against Fox Tempest-enabled attacks 4. Microsoft Defender detections 5. Indicators of compromise Fox Tempest is a financially motivated threat actor that operates a...

How Storm-2949 turned a compromised identity into a cloud-wide breach

In this article 1. Attack chain overview 1. Cloud compromise: Microsoft Entra ID and Microsoft 365 2. Initial access and persistence through targeted social engineering and SSPR abuse 3. Directory discovery and persistence 4. Microsoft 365 discovery and exfiltration 5. Cloud compromise: Microsoft...

How Storm-2949 turned a compromised identity into a cloud-wide breach

In this article 1. Attack chain overview 1. Cloud compromise: Microsoft Entra ID and Microsoft 365 2. Initial access and persistence through targeted social engineering and SSPR abuse 3. Directory discovery and persistence 4. Microsoft 365 discovery and exfiltration 5. Cloud compromise: Microsoft...

How to better protect your growing business in an AI-powered world

AI is rapidly reshaping how work gets done in companies and organizations. In celebrating National Small Business Month, we want to acknowledge the unique challenges that growing business leaders face as AI creates both opportunity and risk. They face constant tradeoffs between moving fast,...

Defense in depth for autonomous AI agents

Designing Secure Autonomous AI Agents with Defense in Depth AI agents are moving beyond assistance and into action. Instead of generating content, they invoke tools, modify data, trigger workflows, and operate across systems with increasing autonomy. This shift changes the security problem...

Defense in depth for autonomous AI agents

Designing Secure Autonomous AI Agents with Defense in Depth AI agents are moving beyond assistance and into action. Instead of generating content, they invoke tools, modify data, trigger workflows, and operate across systems with increasing autonomy. This shift changes the security problem...

Kazuar: Anatomy of a nation-state botnet

In this article 1. Delivery 2. Module types 3. Botnet operations 4. Who is Secret Blizzard? 5. Mitigation and protection guidance 6. Microsoft Defender detections Kazuar, a sophisticated malware family attributed to the Russian state actor Secret Blizzard, has been under constant development for...

Kazuar: Anatomy of a nation-state botnet

In this article 1. Delivery 2. Module types 3. Botnet operations 4. Who is Secret Blizzard? 5. Mitigation and protection guidance 6. Microsoft Defender detections Kazuar, a sophisticated malware family attributed to the Russian state actor Secret Blizzard, has been under constant development for...

When configuration becomes a vulnerability: Exploitable misconfigurations in AI apps

In this article 1. Background 2. What is an exploitable misconfiguration? 3. Exploitable misconfigurations in popular AI applications 4. Minimizing the risk: Practical deployment guidance 5. How Microsoft Defender for Cloud helps detect exposures in Kubernetes 6. Learn more AI and agentic...

When configuration becomes a vulnerability: Exploitable misconfigurations in AI apps

In this article 1. Background 2. What is an exploitable misconfiguration? 3. Exploitable misconfigurations in popular AI applications 4. Minimizing the risk: Practical deployment guidance 5. How Microsoft Defender for Cloud helps detect exposures in Kubernetes 6. Learn more AI and agentic...

Accelerating detection engineering using AI-assisted synthetic attack logs generation

In this article 1. Core Idea: From TTPs to Logs 2. Approaches for Synthetic Attack Log Generation 3. Evaluation Datasets 4. References 5. Learn more Logs and telemetry are the foundation of modern cybersecurity. They enable threat detection, incident response, forensic investigation, and complian...

Accelerating detection engineering using AI-assisted synthetic attack logs generation

In this article 1. Core Idea: From TTPs to Logs 2. Approaches for Synthetic Attack Log Generation 3. Evaluation Datasets 4. References 5. Learn more Logs and telemetry are the foundation of modern cybersecurity. They enable threat detection, incident response, forensic investigation, and complian...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark

In this article 1. AI-powered vulnerability discovery at hyper-scale 2. Codename: MDASH—Microsoft Security’s new multi-model agentic scanning harness 3. Using codename MDASH for security research 4. The 5.12.2026 Patch Tuesday cohort 5. Two deep dives 1. CVE-2026-33827—Remote unauthenticated UAF ...

Defending consumer web properties against modern DDoS attacks

If you own, create, or maintain online services and web portals, you’re probably aware of the dramatic upswing in DDoS attacks on your domains. AI has democratized tooling not just for us but for threat actors as well. DDoS in this era has extended from simple bandwidth saturation to sophisticate...

Undermining the trust boundary: Investigating a stealthy intrusion through third-party compromise

In this article 1. Abuse of trusted relationships as an attack delivery mechanism 2. Methods, tools, and access strategies 3. Campaign conclusion 4. Microsoft Defender detection and hunting guidance In recent years, many sophisticated intrusions have increasingly avoided using noisy exploits,...

Undermining the trust boundary: Investigating a stealthy intrusion through third-party compromise

In this article 1. Abuse of trusted relationships as an attack delivery mechanism 2. Methods, tools, and access strategies 3. Campaign conclusion 4. Microsoft Defender detection and hunting guidance In recent years, many sophisticated intrusions have increasingly avoided using noisy exploits,...

Active attack: Dirty Frag Linux vulnerability expands post-compromise risk

In this article 1. Why Dirty Frag matters 2. Technical overview 3. Exploitation scenarios 4. Mitigation guidance 5. Post-mitigation integrity verification 6. References A newly disclosed Linux local privilege escalation vulnerability known as “Dirty Frag” enables escalation from an unprivileged...

Active attack: Dirty Frag Linux vulnerability expands post-compromise risk

In this article 1. Why Dirty Frag matters 2. Technical overview 3. Exploitation scenarios 4. Mitigation guidance 5. Post-mitigation integrity verification 6. References A newly disclosed Linux local privilege escalation vulnerability known as “Dirty Frag” enables escalation from an unprivileged...

When prompts become shells: RCE vulnerabilities in AI agent frameworks

In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...

When prompts become shells: RCE vulnerabilities in AI agent frameworks

In this article 1. A representative case study: Semantic Kernel 2. CVE-2026-26030: In-Memory Vector Store 3. CVE-2026-25592: Arbitrary file write through SessionsPythonPlugin 4. The vulnerability 5. Attack chain overview 6. Defending the agentic edge 7. Not bugs, but developed by design 8. CTF...

World Passkey Day: Advancing passwordless authentication

World Passkey Day is a chance to reflect on progress toward a shared goal: reducing our reliance on passwords and other phishable authentication methods by accelerating passkey adoption. As cyberattacks become more automated and AI-powered, each account is only as secure as its weakest credential...

World Passkey Day: Advancing passwordless authentication

World Passkey Day is a chance to reflect on progress toward a shared goal: reducing our reliance on passwords and other phishable authentication methods by accelerating passkey adoption. As cyberattacks become more automated and AI-powered, each account is only as secure as its weakest credential...

​​Microsoft named an overall leader in KuppingerCole Analyst’s 2026 Emerging AI Security Operations Center (SOC) report ​​

Security operations are entering a new phase. As attack techniques grow faster and more complex, the effectiveness of a SOC depends less on collecting more data and more on how well platforms can turn context into action at scale. KuppingerCole Analysts’ 2026 Emerging AI Security Operations Cente...

ClickFix campaign uses fake macOS utilities lures to deliver infostealers

In this article 1. Activity overview 2. Mitigation and protection guidance 3. Hunting queries 4. Indicators of compromise Microsoft researchers continue to observe the evolution of an infostealer campaign distributing ClickFix‑style instructions and targeting macOS users. In this recent iteration...

Breaking the code: Multi-stage ‘code of conduct’ phishing campaign leads to AiTM token compromise

In this article 1. Multi-step social engineering campaign leading to credential theft 2. Mitigation and protection guidance 3. Microsoft Defender detections 4. Hunting queries 5. Indicators of compromise Phishing campaigns continue to improve sophistication and refinement in blending social...