Latest cybersecurity reporting from selected sources.

Huntress found an AI-generated PowerShell script used for AD reconnaissance, showing attackers are using AI to create custom, evasive tools. During an incident response investigation on June 3, 2026, Huntress analyst Jevon Ang recovered a PowerShell script from a compromised Windows Server that the attacker had used to map out the victim’s Active Directory environment. […]

A new phishing-as-a-service (PhaaS) operation called Forg365 is using a combination of device code phishing, adversary-in-the-middle (AitM) tactics, antibot evasion, artificial intelligence (AI)-assisted lure creation, and post-compromise mailbox operations targeting Microsoft 365 accounts

Microsoft-Owned GitHub, Which Runs npm, Previews Supply-Chain Security FixesThe popular Mastra AI framework, used to build artificial intelligence agents, workflows and retrieval-augmented generation pipelines, has been poisoned by attackers, and Microsoft-owned GitHub has advised all developers to downgrade Mastra, pending compromised packages being found and eradicated.

The Miasma worm compromised 73 Microsoft GitHub repos, spreading via AI coding tools and stealing cloud credentials from developers and CI/CD systems. A self-replicating worm called Miasma has compromised 73 Microsoft GitHub repositories and forced GitHub staff to disable them. The affected repos include core Azure infrastructure like azure-functions-host and the entire Durable Task family […]

Attackers Compromised More Than 70 Microsoft Repositories in Under 2 MinutesAttackers linked to the Miasma supply-chain campaign compromised a Microsoft contributor account and pushed malicious code into more than 70 repositories, using artificial intelligence-assisted coding tools as an infection path to steal credentials and developer secrets at scale.

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 mitigations teams need now. The post Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us  appeared first on Microsoft Security Blog.

Who needs MFA when you've got EvilTokens? Hundreds of organizations have been compromised daily by a Microsoft device-code phishing campaign that uses AI and automation at nearly every stage of the attack chain to ultimately snoop through corporate email inboxes and steal financial data.…

Anthropic's Mythos Leak Points to Pattern of Failures, Sloppy Practices at AI LabsAnthropic accidentally exposed its most powerful unreleased AI model to compromise, and days later shipped its flagship coding tool's full source code without meaning to. Meta, Microsoft and OpenAI have each had comparable moments. Questions linger about the integrity of third-party AI tools.

Jim DuBois, Former Microsoft CIO and CISO, on Incentives, AI and Cyber's FutureAs AI reshapes cybersecurity, aligning security and innovation teams is more critical than ever. Former Microsoft CIO and CISO Jim DuBois says misaligned incentives create conflict, and fixing that is what lets organizations move fast without compromising security.

The North Korea-linked threat actor known as UNC1069 has been observed targeting the cryptocurrency sector to steal sensitive data from Windows and macOS systems with the ultimate goal of facilitating financial theft

Cybersecurity researchers have flagged a new malicious Microsoft Visual Studio Code (VS Code) extension for Moltbot (formerly Clawdbot) on the official Extension Marketplace that claims to be a free artificial intelligence (AI) coding assistant, but stealthily drops a malicious payload on compromised hosts

Cybersecurity researchers have disclosed details of a new attack method dubbed Reprompt that could allow bad actors to exfiltrate sensitive data from artificial intelligence (AI) chatbots like Microsoft Copilot in a single click, while bypassing enterprise security controls entirely

Microsoft has disclosed details of a novel backdoor dubbed SesameOp that uses OpenAI Assistants Application Programming Interface (API) for command-and-control (C2) communications

Ukraine’s CERT-UA has identified a new AI-powered malware, dubbed “LameHug,” which executes commands on compromised Windows systems in cyber-attacks, targeting the nation’s security and defense sector

A novel malware family named LameHug is using a large language model (LLM) to generate commands to be executed on compromised Windows systems. [...]

Attack Method Exploits RAG-based Tech to Manipulate AI System's OutputResearchers found an easy way to manipulate the responses of an artificial intelligence system that makes up the backend of tools such as Microsoft 365 Copilot, potentially compromising confidential information and exacerbating misinformation. Researchers called the attack "ConfusedPilot."

Attackers can introduce a malicious document in systems such as Microsoft 365 Copilot to confuse the system, potentially leading to widespread misinformation and compromised decision-making processes.

The SmokeLoader malware is being used to deliver a new Wi-Fi scanning malware strain called Whiffy Recon on compromised Windows machines