Hugging Face Breached by Autonomous AI Agent in First-of-Its-Kind Attack
Hugging Face, the world's largest open-source AI model repository, disclosed a security breach perpetrated by an autonomous AI agent system. The attack…
Tag: AI Security
Hugging Face: Open-Source AI Platform Breached by Autonomous AI Agent
Hugging Face, the leading open-source AI model repository, suffered a breach where an autonomous AI agent exploited code execution paths in its…
NadMesh Botnet Targets Exposed AI Services for Cloud Credentials and Kubernetes Tokens
A new Go-based botnet named NadMesh has been discovered actively hunting exposed AI services to steal cloud credentials and Kubernetes tokens. First…
NadMesh Botnet: A Go-Based Threat Targeting AI Services
NadMesh is a Go-based botnet discovered in July 2026 that targets exposed AI services to steal cloud credentials and Kubernetes tokens. It…
Agent Data Injection (ADI) Attack: How AI Agents Can Be Tricked Into Misclicking or Running Attacker Commands
A new class of attack called Agent Data Injection (ADI) has been disclosed by researchers from Seoul National University, the University of…
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery to fix issues before tools…
Andon Labs AI Vending Machine Targeted in GPT-Red Test
OpenAI used GPT-Red to attack an AI-based vending machine built by Andon Labs, successfully lowering prices and canceling orders in a real-world…
GPT-Red: OpenAI’s Automated Red-Teaming Model
GPT-Red is an internal automated red-teaming model that scales prompt injection vulnerability discovery by iteratively sending prompts and monitoring responses to achieve…
GPT-5.4 mini: Model Used in Codex Agent Attack
GPT-5.4 mini was used as the base model for a Codex command-line agent that was attacked by GPT-Red in a case study…
SASE Has an AI Blind Spot: Why Packet Inspection Falls Short in Modern Enterprise Security
For years, routing traffic through cloud proxies was sufficient for enterprise security. However, the shift to browser-based work, SaaS applications, and generative…