⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More
https://ift.tt/Ef5pkGH starts with the usual promise that everything is under control. Then the logs wake
ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link
https://ift.tt/wWYqksc researchers have disclosed a critical vulnerability in OpenAI’s ChatGPT Workspace Agents that could have
Seeing AI Agents Is Not Enough. Security Teams Must Enforce What They Can Do
https://ift.tt/M0BYFTi agent security is moving through a familiar maturity curve: adoption, then visibility, and finally,
Hacker Runs Hermes AI Agent Unattended for Post-Exploitation at Thai Finance Ministry
https://ift.tt/w4zKsPb installed a popular AI assistant on a rented server, switched off the setting that
NodeBB Patches Eight AI-Found Flaws Exposing Admin Access and Private Chats
https://ift.tt/WGMjNAt security flaws in NodeBB went public on Wednesday, along with the code to exploit
ThreatsDay: Android Spyware, PLC Attacks, AI Image Prompt Injection + 12 More Stories
https://ift.tt/ARNgP81 of this week’s trouble came dressed as something useful. A package stole data. A
Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files
https://ift.tt/bIs64Qq researchers have uncovered a sandbox escape vulnerability in Anthropic’s Claude Cowork that makes it
China-Nexus JadeProx Uses New TriBack Loader in Government and Healthcare Attacks
An exposed Alibaba Cloud server has revealed a China-nexus operation that Group-IB tracks as JadeProx.
Agentic AI Challenges Progress in Confidential Computing
Core issues that slowed down adoption of secure data vaults are being resolved by technology,
ANCHOR-CI could fix 20 years of broken government-industry collaboration
On July 1, the Cybersecurity and Infrastructure Security Agency (CISA) published a seven-page notice in