Adaptive Spec-driven Scoring for Evaluation and Regression Testing (ASSERT) is an open-source framework for converting natural language behavior requirements into executable evaluations of AI models and agents. The post Turn specs into evals for any agent with ASSERT appeared first…
Category: Microsoft Security Blog
Reconstructing AI activity in investigations
Learn how to investigate AI activity in Microsoft 365 Copilot and Azure AI services using a structured, telemetry-driven approach. This playbook helps security teams reconstruct events, assess data exposure, and detect potential threats faster. The post Reconstructing AI activity in…
AI brands as bait: How threat actors are using the AI hype in social engineering
As threat actors operationalize AI to accelerate attacks, they are also leveraging the wider global interest around AI itself as a social engineering lure. The post AI brands as bait: How threat actors are using the AI hype in social…
Securing CI/CD in an agentic world: Claude Code Github action case
Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack chain, responsible disclosure process, Anthropic’s mitigation, and guidance for securing AI-powered CI/CD workflows.…
Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us
A surge in real-world attacks against agentic AI systems is reshaping how we think about risk. Based on 12 months of red teaming, this update introduces seven new failure modes, from supply chain compromise to goal hijacking, and the practical…
Preinstall to persistence: Inside the Red Hat npm Miasma credential-stealing campaign
A large-scale npm supply chain attack compromised over 90 versions of @redhat-cloud-services packages, silently infecting CI/CD environments and developer systems. The malicious code steals credentials from GitHub, cloud platforms, and local machines, then spreads like a worm by republishing trusted…
Microsoft Build 2026: Securing code, agents, and models across the development lifecycle
Discover how Microsoft enables fast, secure AI development with MDASH and new security capabilities. The post Microsoft Build 2026: Securing code, agents, and models across the development lifecycle appeared first on Microsoft Security Blog. This article has been indexed from…
Malicious npm packages abuse dependency confusion to profile developer environments
A dependency confusion campaign leveraged 33 malicious npm packages to collect reconnaissance data from developer and build environments. This report details the attack chain, observed tradecraft, and detection opportunities to help organizations identify and disrupt related activity. The post Malicious…
Microsoft is named a Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection
Microsoft is named a Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection. The post Microsoft is named a Leader in the 2026 Gartner® Magic Quadrant™ for Endpoint Protection appeared first on Microsoft Security Blog. This article has been…
Typosquatted npm packages used to steal cloud and CI/CD secrets
The Mini Shai-Hulud campaign used malicious npm packages to target cloud and CI/CD credentials across developer environments. This report details the attack chain, detection opportunities, and mitigation guidance to help organizations identify and disrupt related activity. The post Typosquatted npm…
The Gentlemen ransomware: Dissecting a self-propagating Go encryptor
Microsoft Threat Intelligence presents a comprehensive analysis of The Gentlemen, a Go-based ransomware deployed by affiliates of Storm-2697 that combines per-file ephemeral key encryption with an aggressive self-propagation module to deploy itself across an entire network using series of simultaneous…
From poisoned search results to GPU mining: A cryptojacking campaign abusing ScreenConnect and Microsoft .NET utilities
Microsoft exposes a cryptojacking campaign using SEO poisoning and ScreenConnect to target high-performance PCs, with malicious sites also surfaced through AI chatbots. The post From poisoned search results to GPU mining: A cryptojacking campaign abusing ScreenConnect and Microsoft .NET utilities…
Microsoft recognized as a Leader in The Forrester Wave™ for Workforce Identity Security Platforms
Microsoft has been recognized as a Leader in The Forrester Wave™: Workforce Identity Security Platforms, Q2 2026, receiving the highest scores in both the current offering and strategy categories. The post Microsoft recognized as a Leader in The Forrester Wave™…
Microsoft Security success stories: How St. Luke’s and ManpowerGroup are securing AI foundations
How Frontier firms secure AI at scale: read how Microsoft customers embed governance, identity, and cloud security to make protection an enabler of AI growth. The post Microsoft Security success stories: How St. Luke’s and ManpowerGroup are securing AI foundations…
From edge appliance to enterprise compromise: Multi-stage Linux intrusion via F5 and Confluence
A multi-stage attack on Linux devices began with an exposed F5 BIG-IP edge appliance and pivoted to an internal Confluence server for credential theft and identity compromise. Learn how the threat actor attempted Kerberos relay and lateral movement, and how…
What’s new in Microsoft Security: May 2026
Microsoft Security’s latest updates extend visibility, control, and protection across expanding ecosystems as organizations accelerate AI adoption. The post What’s new in Microsoft Security: May 2026 appeared first on Microsoft Security Blog. This article has been indexed from Microsoft Security…
Mini Shai Hulud: Compromised @antv npm packages enable CI/CD credential theft
Compromised @antv npm packages deploy the Mini Shai-Hulud payload to steal CI/CD secrets from Linux-based automation environments. The malware executes during npm install and targets credentials across GitHub, AWS, Kubernetes, Vault, npm, and 1Password platforms. The post Mini Shai Hulud:…
Securing the gaming culture of cultures
Read about the unique challenges and rewards of securing gaming platforms and how to better protect gaming communities. The post Securing the gaming culture of cultures appeared first on Microsoft Security Blog. This article has been indexed from Microsoft Security…
Introducing RAMPART and Clarity: Open source tools to bring safety into Agent development workflow
The AI systems shipping inside enterprises today are fundamentally different from the ones we were building even two years ago, because they have moved well past answering questions and into accessing your email, retrieving records from your CRM, writing and…
Exposing Fox Tempest: A malware-signing service operation
Fox Tempest is a financially motivated threat actor operating a malware‑signing‑as‑a‑service (MSaaS) used by other cybercriminals, including Vanilla Tempest and Storm groups, to more effectively distribute malicious code, including ransomware. The post Exposing Fox Tempest: A malware-signing service operation appeared…