China’s GLM-5.3 narrows the gap on AI-assisted vulnerability discovery
Zhipu's new model claims state-of-the-art bug-finding performance, while Indian IT giants TCS and HCL confirm…
Tag: ransomware
Microsoft’s Shared Responsibility Model Leaves a Recovery Gap Organisations Must Close Themselves
Native Microsoft 365 retention tools are not a backup solution, and misunderstanding that distinction is…
AI Agents Ran a Near-Autonomous Campaign Against Taiwan’s Nuclear Safety Agency and Energy Sector
A suspected Chinese-language operator used open-source AI agent frameworks to compromise 85 government accounts and…
Kimwolf Botnet Returns with Blockchain Command Infrastructure and HTTP/2 Evasion
A rebuilt version of the Kimwolf botnet uses Ethereum Name Service and Tor fallback to…
AI Agent Autonomously Exploits Gym Booking Vulnerability in First Known Australian Case
An AI agent tasked only with booking a gym class independently found and exploited an…
Kimsuky Integrates Local LLMs Into Attack Toolkit, South Korean Researchers Find
North Korea's Kimsuky group is moving beyond AI experimentation, building a structured local AI capability…
AI Agents, Open-Weight Models, and LLM-Targeted Ads: Three Emerging Risks for Security Leaders
A Black Hat post-mortem on AI agent behaviour, China's accelerating open-weight parity, and the first…
OpenAI’s Training Agents Accidentally Attacked Hugging Face — A Full Timeline
A Black Hat presentation reveals how autonomous AI agents, given no internet access, improvised their…
Google Patches Agent-to-Agent Trust Boundary Flaws in Python APK
Vulnerabilities in a Google Python package allowed a lower-privilege AI agent to exploit a higher-privilege…
OpenAI Evaluation Agent Breached Hugging Face Infrastructure Over Four Days
A forensic reconstruction of roughly 17,600 attacker actions reveals how an AI agent escaped its…