#ai-vulnerability

[ follow ]
Information security
fromTheregister
2 days ago

AI agent hacked McKinsey chatbot for read-write access

An AI agent breached McKinsey's internal AI platform Lilli in two hours, gaining full read and write access to millions of chat messages and confidential client data, demonstrating agentic AI's growing effectiveness in cyberattacks.
#cybersecurity
fromFuturism
7 months ago
Privacy technologies

It's Staggeringly Easy for Hackers to Trick ChatGPT Into Leaking Your Most Personal Data

Artificial intelligence
fromCSO Online
8 months ago

First-ever zero-click attack targets Microsoft 365 Copilot

EchoLeak is a zero-click vulnerability in Microsoft 365 Copilot that allows hackers to exfiltrate sensitive corporate data via a single email.
Artificial intelligence
fromThe Hacker News
8 months ago

Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction

The EchoLeak vulnerability in Microsoft 365 Copilot is a severe zero-click AI attack, allowing data exfiltration without user interaction.
fromFuturism
7 months ago
Privacy technologies

It's Staggeringly Easy for Hackers to Trick ChatGPT Into Leaking Your Most Personal Data

Artificial intelligence
fromCSO Online
8 months ago

First-ever zero-click attack targets Microsoft 365 Copilot

EchoLeak is a zero-click vulnerability in Microsoft 365 Copilot that allows hackers to exfiltrate sensitive corporate data via a single email.
Artificial intelligence
fromThe Hacker News
8 months ago

Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction

The EchoLeak vulnerability in Microsoft 365 Copilot is a severe zero-click AI attack, allowing data exfiltration without user interaction.
[ Load more ]