Tag

#Varonis

8 stories taggedVaronis.

A researcher's computer showing a chat interface with an AI assistant, with internal system information and security weaknesses being revealed in the conversati
AI Security

Researchers Tricked Microsoft Copilot Into Revealing Its Own Weaknesses, Then Used That Knowledge to Steal Data

A research team at Varonis discovered that simply chatting with Microsoft's AI assistant could expose enough internal detail to build a working attack. Microsoft has patched the flaws, but the technique raises questions that go well beyond one product.

4 min read
A Copilot AI assistant interface on screen showing connected applications like Gmail and calendar services, with warning indicators highlighting data leakage vu
AI Security

One Click on Copilot Could Have Leaked Your Connected Apps, Researchers Say

Three flaws in Microsoft Copilot Personal, nicknamed CoSnitch, let a booby-trapped link quietly pull data from Gmail, calendars and other services the assistant was connected to.

4 min read
A computer mouse pointer hovering over a link in an email interface, with office collaboration tool icons visible on the background desktop
AI Security

A Single Click Could Have Handed Hackers Your Company's Confluence and Jira Files

Researchers found a flaw in Atlassian's Rovo AI assistant that let an attacker steal data from widely used workplace tools with almost no effort from the victim.

2 min read
A computer screen showing an AI agent's intended actions versus its permitted scope, with visual indicators showing where the agent's behavior deviates from gua
AI Security

Varonis pitches 'intent-based' guardrails for AI agents that stray off task

Agent IBAC watches what an AI agent is trying to do, not just what it is allowed to touch, and pulls the brakes when the two drift apart.

4 min read
A cybercrime forum listing page for Dolphin X malware, displaying a scoring algorithm interface that ranks infected machines by financial value and net worth es
Threat Intelligence

Dolphin X: The New Malware That Uses AI to Pick Which Victims to Rob First

A remote access trojan sold on a cybercrime forum claims to score infected machines by their value, so criminals can go after the richest targets first.

4 min read
Illustration: a sunlit tropical beach at golden hour with a laptop open on a wooden table in the foreground
Identity & Access

Varonis Launches Free Entra ID Training Game to Teach Cloud Identity Attacks

Breach at the Beach is a browser-based challenge that walks defenders through the kind of Microsoft Entra ID attacks Varonis researchers say they see in real customer environments.

4 min read
Illustration: A softly lit modern office desk at night with a laptop screen showing an abstract chat interface
Cloud Security

Google Chatbot Flaw Let Attackers Hijack Other Bots and Read User Chats

A bug in Google Dialogflow CX, patched after a Varonis report, could have let one rogue chatbot spy on and puppet others sharing the same cloud project.

3 min read
Illustration: Macro close-up of a glowing blue search bar interface on a dark enterprise dashboard screen
AI Security

SearchLeak Shows How a Single Crafted URL Can Drain Your M365 Tenant

Varonis researchers chained three weaknesses in Copilot Enterprise Search into a full data-exfiltration path. Microsoft patched it. The attack class isn't going anywhere.

3 min read
© 2026 Threat Vectr