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. […]

TrendAI™ Research analyzed over 200 Gemini CLI session logs showing how a Russian-speaking threat actor used AI to run a live botnet, finishing a full C&C migration in six minutes while doing just 11% of the work himself.

Malware Harvested Cloud Credentials, Source Code and Deployment TokensAttackers used a compromised npm publishing credential to release five malicious versions of Jscrambler's Code Integrity package, deploying a Rust-based infostealer that harvested developer, cloud and AI tool credentials while evolving its delivery methods to evade detection.

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

Sygnia report details how agentic AI accelerated weeks-long attack to just 72 hours

Cybersecurity researchers have disclosed details of a now-patched critical session isolation vulnerability in Writer, an enterprise generative artificial intelligence (AI) platform, that could result in cross-tenant compromise

Tomorrow's webinar explores how behavioral AI can help organizations detect sophisticated phishing, business email compromise, and account takeover attacks while reducing alert fatigue through automated investigation and response workflows. [...]

Attacks also used a compromised chatbot in campaign to steal sensitive information from Business Users

Business email compromise attacks increasingly rely on convincing impersonation rather than malware, making them harder for employees and traditional email defenses to detect. This webinar explores how behavioral AI can help identify sophisticated email threats and automate response workflows. [...]

Modern phishing attacks, including Device Code phishing, can undermine MFA protections and grant attackers access to corporate accounts without stealing passwords. This webinar explores how behavioral AI can help security teams detect compromised accounts faster and automate response workflows. [...]

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.

As many as 145 npm packages associated with the Mastra namespace ("@mastra/*"), a popular open-source JavaScript and TypeScript framework for building artificial intelligence (AI) applications, have been compromised as part of a software supply chain attack codenamed easy-day-js, per findings from Endor Labs, JFrog, OX Security, SafeDep, Socket, StepSecurity, and Synk

Phishing simulation on an OpenClaw email agent with various configuration profiles showed that it was susceptible to tactics commonly used to compromise human users. [...]

Laure Lydon of Flo Health on Securing AI Without Compromising TrustTrust in femtech isn't a feature. It's the foundation. Laure Lydon, vice president of security at Flo Health, makes the case for embedding privacy and security into AI development from day one, not as an afterthought. Firms must evaluate potential risks before systems are built, she said.

iBiz might not win the AI race, but analysts say it's focusing on features people may actually use

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 […]

Victims Increasingly Face Multiple Compromises From a Single IncidentIdentity theft scams are increasingly unfolding as coordinated, AI-assisted attack chains that begin with phishing or impersonation escalate into account takeovers, device compromise and broader fraud, according to the Identity Theft Resource Center.

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.

Chainable Bugs Enable Credential Theft, Persistence, TakeoverFour chainable flaws in OpenClaw allowed attackers to move from an initial foothold to persistent system-level compromise by abusing the AI agent's own privileges. The bugs enabled credential theft, privilege escalation and backdoor deployment, affecting all versions released before April 23.