Threat actors abused trusted Trivy distribution channels to inject credential‑stealing malware into CI/CD pipelines worldwide. This analysis walks through the Trivy supply‑chain compromise, attacker techniques, and concrete steps security teams can take to detect and defend against similar attacks. The…
Tag: Microsoft Security Blog
Governing AI agent behavior: Aligning user, developer, role, and organizational intent
This research report explores the layers of agent intent and how to align them for secure enterprise AI adoption. The post Governing AI agent behavior: Aligning user, developer, role, and organizational intent appeared first on Microsoft Security Blog. This article…
Case study: How predictive shielding in Defender stopped GPO-based ransomware before it started
Microsoft Defender stopped a human-operated ransomware attack that abused Group Policy Objects (GPOs) to disable defenses and push encryption at scale. This case study breaks down the attacker’s playbook and shows how predictive shielding hardened 700 devices in time, resulting…
Secure agentic AI end-to-end
In this agentic era, security must be woven into, and around, every layer of the AI estate. At RSAC 2026, we are delivering on that vision with new purpose-built capabilities designed to help organizations secure agents, secure their foundations, and…
CTI-REALM: A new benchmark for end-to-end detection rule generation with AI agents
Excerpt: CTI-REALM is Microsoft’s open-source benchmark for evaluating AI agents on real-world detection engineering—turning cyber threat intelligence (CTI) into validated detections. The post CTI-REALM: A new benchmark for end-to-end detection rule generation with AI agents appeared first on Microsoft Security…
New tools and guidance: Announcing Zero Trust for AI
Microsoft introduces Zero Trust for AI, adding a new AI pillar to its workshop, enhanced reference architecture, updated guidance, and a new assessment tool. The post New tools and guidance: Announcing Zero Trust for AI appeared first on Microsoft Security…
When tax season becomes cyberattack season: Phishing and malware campaigns using tax-related lures
In recent months, Microsoft Threat Intelligence identified email campaigns using lures around W-2, tax forms, or similar themes, or posing as government tax agencies, tax services firms, and relevant financial institutions, with many campaigns targeting individuals for personal and financial…
Observability for AI Systems: Strengthening visibility for proactive risk detection
As AI systems grow more autonomous, observability becomes essential. Learn how visibility into AI behavior helps detect risk and strengthen secure development. The post Observability for AI Systems: Strengthening visibility for proactive risk detection appeared first on Microsoft Security Blog.…
New Microsoft Purview innovations for Fabric to safely accelerate your AI transformation
As organizations adopt AI, security and governance remain core primitives for safe AI transformation and acceleration. The post New Microsoft Purview innovations for Fabric to safely accelerate your AI transformation appeared first on Microsoft Security Blog. This article has been…
Help on the line: How a Microsoft Teams support call led to compromise
A DART investigation into a Microsoft Teams voice phishing attack shows how deception and trusted tools can enable identity-led intrusions and how to stop them. The post Help on the line: How a Microsoft Teams support call led to compromise…
Storm-2561 uses SEO poisoning to distribute fake VPN clients for credential theft
Storm-2561 uses SEO poisoning to push fake VPN downloads that install signed trojans and steal VPN credentials. Active since 2025, Storm-2561 mimics trusted brands and abuses legitimate services. This post reviews TTPs, IOCs, and mitigation guidance. The post Storm-2561 uses…
From transparency to action: What the latest Microsoft email security benchmark reveals
The latest Microsoft benchmarking data reveals how Microsoft Defender mitigates modern email threats compared to SEG and ICES vendors. The post From transparency to action: What the latest Microsoft email security benchmark reveals appeared first on Microsoft Security Blog. This…
Detecting and analyzing prompt abuse in AI tools
Hidden instructions in content can subtly bias AI, and our scenario shows how prompt injection works, highlighting the need for oversight and a structured response playbook. The post Detecting and analyzing prompt abuse in AI tools appeared first on Microsoft…
Contagious Interview: Malware delivered through fake developer job interviews
The Contagious Interview campaign weaponizes job recruitment to target developers. Threat actors pose as recruiters from crypto and AI companies and deliver backdoors such as OtterCookie and FlexibleFerret through fake coding assessments. The malware then steals API tokens, cloud credentials,…
Secure agentic AI for your Frontier Transformation
Learn how Microsoft Agent 365 and Microsoft 365 E7 can help secure your Frontier Transformation. The post Secure agentic AI for your Frontier Transformation appeared first on Microsoft Security Blog. This article has been indexed from Microsoft Security Blog Read…
AI as tradecraft: How threat actors operationalize AI
Threat actors are operationalizing AI to scale and sustain malicious activity, accelerating tradecraft and increasing risk for defenders, as illustrated by recent activity from North Korean groups such as Jasper Sleet and Coral Sleet (formerly Storm-1877). The post AI as…
Malicious AI Assistant Extensions Harvest LLM Chat Histories
Malicious AI browser extensions collected LLM chat histories and browsing data from platforms such as ChatGPT and DeepSeek. With nearly 900,000 installs and activity across more than 20,000 enterprise tenants, the campaign highlights the growing risk of data exposure through…
Women’s History Month: Encouraging women in cybersecurity at every career stage
This Women’s History Month, we explore ways to support the next generation of female defenders at every career stage. The post Women’s History Month: Encouraging women in cybersecurity at every career stage appeared first on Microsoft Security Blog. This article…
Inside Tycoon2FA: How a leading AiTM phishing kit operated at scale
Tycoon2FA has become a leading phishing-as-a-service (PhaaS) platforms, enabling campaigns that reach over 500,000 organizations monthly, prompting Microsoft’s Digital Crimes Unit (DCU) to work with Europol and industry partners to facilitate a disruption of Tycoon2FA’s infrastructure and operations. The post…
Signed malware impersonating workplace apps deploys RMM backdoors
Signed malware backed by a stolen EV certificate deployed legitimate RMM tools to gain persistent access inside enterprise environments. Organizations must harden certificate controls and monitor RMM activity to reduce exposure. The post Signed malware impersonating workplace apps deploys RMM…