Thursday, August 7, 2025

Zenity Labs Uncovers AgentFlayer Flaws in Enterprise AI

Related stories

Oxmiq Labs™: Rebuilding the GPU Stack from Atoms to Agents

Oxmiq Labs, the all-new GPU software and IP startup founded...

Ganymede Unveils AI Platform for R&D and Manufacturing

Ganymede, the scientific data cloud, announced the launch of...

Tuskira Enhances Agentic AI for Security Operations

Now simulating unpatched threats, tracing business risk, and responding...

Noma Security Debuts First Full AI Agent Security Solution

Company leads the market with specialized agent security, enabling...

SK Telecom Unveils NVIDIA-Powered Sovereign AI System

SK Telecom builds AI Infrastructure with over 1,000 NVIDIA...
spot_imgspot_img

Groundbreaking research reveals working 0click compromises of OpenAI’s ChatGPT, Microsoft Copilot Studio, Salesforce Einstein, Cursor, and more, exposing widespread vulnerabilities across production AI environments

Zenity Labs revealed AgentFlayer, a comprehensive set of 0click exploit chains that allow attackers to silently compromise enterprise AI agents and assistants without requiring any user action. The research, presented by Zenity co-founder and CTO Michael Bargury and threat researcher Tamir Ishay Sharbat in their session, “AI Enterprise Compromise: 0Click Exploit Methods,” demonstrates how widely deployed AI agents from major vendors can be hijacked to exfiltrate data, manipulate workflows, and act autonomously across enterprise systems all while users remain completely unaware.

Subscribe

- Never miss a story with notifications


    Latest stories

    spot_img