Latest cybersecurity reporting from selected sources.

Cybersecurity researchers have flagged a new malware artifact generated using DeepSeek that constructed a novel attack path combining "unrealistic browser-malware concepts with a real browser capability" to turn it into a working ransomware technique that runs entirely inside the browser on both Windows and Android devices

New Microsoft research shows how attackers can hijack AI agents that act on a user's behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an outsider

North Korean threat actor Sapphire Sleet has been linked to a supply chain attack targeting Mastra, according to Microsoft security researchers

Microsoft researchers have detailed an exploit chain, named AutoJack, that turns an AI browsing agent into a delivery vehicle for remote code execution

AutoJack is a novel exploit chain showing how a single malicious webpage can turn an AI browsing agent into a remote code execution vector on the host machine. By abusing trust in localhost, missing authentication, and unsafe parameter handling, attackers can trigger arbitrary process execution through AutoGen Studio’s MCP WebSocket. The research highlights a broader pattern - when agents can browse untrusted content and access local services, traditional boundaries like localhost are no longer secure. The post AutoJack: How a single page can RCE the host running your AI agent  appeared first on Microsoft Security Blog.

A study by the University of Toronto shows how artificial intelligence can power autonomous worms capable of tailoring attacks against Windows, Linux and IoT devices. A group of researchers from the University of Toronto has demonstrated how open-source artificial intelligence models can be used to create a new category of computer worms capable of autonomously […]

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. The post Securing CI/CD in an agentic world: Claude Code Github action case appeared first on Microsoft Security Blog.

Cybersecurity researchers have discovered a remote denial-of-service exploit that affects major web servers, including NGINX, Apache HTTPD, Microsoft IIS, Envoy, and Cloudflare Pingora

Hidden Install Settings Let Malicious MCP Links Execute CodeMicrosoft patched a high-severity flaw in Visual Studio Code after researchers found attackers could hide malicious settings inside MCP server install links, giving them persistent access to developer machines through what appeared to be routine artificial intelligence tool installations.

What if you could generate realistic attack telemetry on demand? Explore research methods that translate attacker behaviors (TTPs) into synthetic logs that can trigger detections at scale and without sensitive data. The post Accelerating detection engineering using AI-assisted synthetic attack logs generation appeared first on Microsoft Security Blog.

The high volume of vulnerabilities reflects a growing trend researchers have been anticipating as artificial intelligence models are deployed to find previously uncovered defects in code. The post Microsoft addresses 137 vulnerabilities in May’s Patch Tuesday, including 13 rated critical appeared first on CyberScoop.

System Translates Detection Rules Across Security PlatformsResearchers developed an AI framework that converts threat detection rules between major SIEM platforms including Splunk, Microsoft Sentinel and QRadar. The system uses LLMs and automated validation steps to preserve detection logic during migrations that often require months of manual work.

Microsoft has awarded $2.3 million to security researchers after receiving nearly 700 submissions during this year's Zero Day Quest hacking contest. [...]

Researchers who found the flaws scored beer money bounties and warn the problem is probably pervasive Exclusive Security researchers hijacked three popular AI agents that integrate with GitHub Actions by using a new type of prompt injection attack to steal API keys and access tokens, and the vendors who run agents didn’t disclose the problem.…

Commands Push Lasting Preferences Into AI AssistantsMicrosoft researchers found companies embedding hidden commands in "summarize with AI" buttons to plant lasting brand preferences in assistants' memory. The tactic, dubbed AI recommendation poisoning, exploits persistent memory features to bias future responses.

Cybersecurity researchers have disclosed that artificial intelligence (AI) assistants that support web browsing or URL fetching capabilities can be turned into stealthy command-and-control (C2) relays, a technique that could allow attackers to blend into legitimate enterprise communications and evade detection

New research from Microsoft has revealed that legitimate businesses are gaming artificial intelligence (AI) chatbots via the "Summarize with AI" button that's being increasingly placed on websites in ways that mirror classic search engine poisoning (AI)

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 discovered two malicious Microsoft Visual Studio Code (VS Code) extensions that are advertised as artificial intelligence (AI)-powered coding assistants, but also harbor covert functionality to siphon developer data to China-based servers

Researchers found the popular model context protocol (MCP) servers, which are integral components of AI services, carry serious vulnerabilities.