Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
0 results for “Varonis”
Microsoft Copilot Personal Flaws Could Let One Click Exfiltrate Data From Connected Apps
Varonis Threat Labs identified three security vulnerabilities in Microsoft Copilot Personal—dubbed CoSnitch—that enable unauthorized data exfiltration from connected apps via a single malicious link click, exploiting an undocumented URL parameter exposed by the assistant itself.
Aug 19, 2026
Varonis Agent IBAC keeps AI agents within their intended boundaries
Varonis introduced Agent IBAC, a new access control solution designed to monitor and constrain AI agent behavior in real time by detecting 'intent drift' and enforcing dynamic guardrails.
Aug 4, 2026
Breach at the Beach: Play the Ultimate Entra ID CTF
Varonis launched a free, hands-on Capture the Flag (CTF) exercise called 'Breach at the Beach' to teach cybersecurity defenders how to detect and investigate real-world Entra ID (formerly Azure AD) attack techniques.
Jul 13, 2026
Dialogflow CX 'Rogue Agent' Flaw Enabled AI Chatbot Data Theft
A security vulnerability in Google's Dialogflow CX platform—dubbed a 'rogue agent' flaw—allowed unauthorized data exfiltration from AI chatbots, was reported by Varonis in late 2025, and has since been patched.
Jul 9, 2026
Rogue Agent Flaw Could Have Let Attackers Hijack Google Dialogflow CX Chatbots
A security researcher discovered a critical vulnerability in Google's Dialogflow CX that allowed lateral movement between Code Block-enabled chatbot agents within the same Google Cloud project, enabling unauthorized access to live conversations and data exfiltration.
Jul 9, 2026