Info Security Magazine
6 months, 1 week ago
New Zero-Click Attack Lets ChatGPT User Steal Data
Researchers at Radware discovered new prompt injection attacks in ChatGPT agentic features
Security news aggregator
Latest cybersecurity reporting from selected sources.
Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.
5
headlines in this view
Refine the feed
Search across headline titles and summaries.
Volume over time
Weekly headline count for the current query.
Showing 5 most recent headlines
Filtered view
Info Security Magazine
9 months, 4 weeks ago
Zero-Click Vulnerability in ChatGPT's Agent Enables Silent Gmail Data Theft
Researchers at Radware found a zero-click flaw in ChatGPT Deep Research agent when connected to Gmail and browsing
Info Security Magazine
1 year, 1 month ago
Microsoft 365 Copilot: New Zero-Click AI Vulnerability Allows Corporate Data Theft
Researchers have found a flaw in Microsoft 365 Copilot that allows the exfiltration of sensitive corporate data with a simple email
Bank Info Security
2 years, 4 months ago
A New Self-Spreading, Zero-Click Gen AI Worm Has Arrived!
Researchers Created Worm That Can Exfiltrate Data, Spread Spam and Poison AI ModelsResearchers have created a zero-click, self-spreading worm that can steal personal data through applications that use chatbots powered by generative artificial intelligence. Dubbed Morris II, the malware uses a prompt injection attack vector to trick AI-powered email assistant apps.
The Hacker News
3 years, 2 months ago
Experts Detail New Zero-Click Windows Vulnerability for NTLM Credential Theft
Cybersecurity researchers have shared details about a now-patched security flaw in Windows MSHTML platform that could be abused to bypass integrity protections on targeted machines