ai security

Varonis Threat Labs disclosed SearchLeak on June 15, 2026, describing a now-patched Microsoft 365 Copilot Enterprise Search vulnerability chain that could let an attacker steal emails, MFA codes, files, calendar details, and other indexed workplace data after a victim clicked a crafted Microsoft...

Microsoft fixed CVE-2026-42824, a Microsoft 365 Copilot information-disclosure vulnerability disclosed in June 2026, after Varonis researchers described a one-click “SearchLeak” attack chain that abused Copilot Search, browser rendering behavior, and Microsoft service trust to leak enterprise...

A security report published June 13, 2026, by MalExt Sentry says two browser ad-blocking extensions, Smart Adblocker and Adblock for Browser, secretly intercepted AI conversations and account metadata from roughly 90,000 users across ChatGPT, Claude, Gemini, Copilot, Perplexity, DeepSeek, Grok...

Microsoft on June 2, 2026 announced an early preview of Microsoft Execution Containers, a cross-platform SDK meant to contain AI agents on Windows and WSL while tying local agent activity into Agent 365, Defender, Intune, and Windows 365 for Agents. The move is not just another developer-tooling...

Anthropic’s rumored Claude Mythos successor, reportedly appearing as claude-oceanus-v1-p in red-team testing in early June 2026, has intensified speculation that the company is preparing a broader launch of its most closely watched frontier model within weeks. The leak is not a launch...

Microsoft introduced Microsoft Scout on June 2, 2026, at Build in San Francisco and online as its first “Autopilot” agent for Microsoft 365, an always-on OpenClaw-based assistant that works through Teams, Outlook, OneDrive, SharePoint, the desktop, the browser, and governed Entra identity. The...

Microsoft is urging security teams to red-team AI systems across the entire application stack, not just the model, with Microsoft red teaming executive Craig Nelson emphasizing data connections, backend automation, credentials, and logging in a recent Microsoft Inside Track security video. The...

Microsoft used Build 2026 on June 2 to announce a security stack spanning code, AI agents, and models, including an expanded MDASH preview, Microsoft Defender integration with GitHub Code Security, Agent 365 runtime controls, Windows 365 for Agents availability, Purview protections, and Defender...

Researchers from Zhejiang University, the National University of Singapore, and Nanyang Technological University have demonstrated AudioHijack, a hidden-audio attack presented at the IEEE Symposium on Security and Privacy in San Francisco in May 2026 that can manipulate voice AI systems into...

Microsoft’s May 2026 Patch Tuesday, released on May 12, delivered fixes for at least 118 documented vulnerabilities across Windows, Office, Azure, Dynamics, SQL Server, Edge, Teams, SharePoint, and related products, while major vendors including Apple, Google, Mozilla, and Oracle also pushed...

Microsoft has listed CVE-2026-41094 as a Microsoft Data Formulator remote code execution vulnerability in its Security Update Guide on May 12, 2026, tying the issue to a product that turns data into AI-assisted visualizations and exploratory analysis. The advisory matters less because Data...

Microsoft is moving from warning about AI’s role in cyberattacks to operationalizing AI as a core part of defense. In its April 22, 2026 security blog, the company said new model capabilities are shrinking the gap between vulnerability discovery and exploitation, while also creating an...

Zenity’s presence around Microsoft 365 Copilot, AI agents, and automation is a timely reminder that enterprise AI adoption has moved well beyond experimentation. The core issue is no longer whether organizations will deploy these tools, but whether they can govern them before sensitive data...

The latest round of AI security disclosures is awkward for three of the biggest names in the field: Anthropic, Google, and Microsoft all accepted bug bounty submissions involving prompt injection attacks against AI agent workflows, then left most users without the public paperwork that normally...

Anthropic’s decision to keep Claude Mythos Preview out of the public release channel is more than another cautious product move. It is a signal that frontier AI labs are now confronting a class of systems whose security behavior can no longer be treated as a side effect of capability gains...

Exabeam is staking out a new and important corner of the AI security market: watching the behavior of AI assistants as closely as it watches human users. The company’s latest expansion of Agent Behavior Analytics extends detection and response into OpenAI ChatGPT and Microsoft Copilot, adding to...

Seattle startup Glacis is betting that the next big AI security problem is not model quality, but proof. With former Microsoft Azure product leader Rohit Tatachar now serving as co-founder and CTO, the company is pushing a sharp thesis into the market: enterprises need tamper-proof evidence that...

Exabeam’s latest expansion of Agent Behavior Analytics lands at exactly the moment enterprise security teams are realizing that AI assistants are no longer just productivity add-ons. They are becoming privileged participants in day-to-day work, touching sensitive data, invoking tools, and...

As Microsoft and Google push AI deeper into everyday work surfaces, CIOs are confronting a security problem that looks familiar on paper but behaves very differently in practice. The issue is no longer just where data goes; it is what AI can do with that data once it is inside the browser...

Applying security fundamentals to AI is becoming the defining CISO problem of 2026, and Microsoft’s latest guidance is a useful reminder that the right response is not panic but discipline. In a March 31, 2026 Security blog post, Microsoft Deputy CISOs argue that AI should be treated as...