New PuzzleMask Attack Hides Malicious Prompts in Plain English to Bypass AI Guardrails
Security researchers have disclosed PuzzleMask, a prompt-obfuscation technique that can help malicious instructions slip past lightweight AI safety filters.
The method hides a policy-violating...
AI Coding Agents Become New Infostealer Target for Tokens, Source Code and Sensitive Project Data
Cybercriminals are increasingly targeting local data stored by AI coding agents, including Claude, Cline, Codex, Continue, Cursor, and OpenCode.
Information-stealing malware, commonly called infostealers,...
North Korean Hackers Use AI to Mass-Produce Convincing Phishing Documents
Security researchers have uncovered fresh evidence that North Korean-linked Kimsuky hackers are using artificial intelligence to rapidly create phishing documents that look like routine...
AI-Powered BraZetsu Malware Turns Compromised Corporate PCs Into Tradable Assets
Group-IB has uncovered BraZetsu, a Python-based Windows malware framework designed to help cybercriminals gain, evaluate, and sell access to compromised corporate systems.
The malware...
Hackers Target LiteLLM, RAGFlow and Kestra AI Infrastructure to Steal API Keys and Mine Crypto
Hackers are increasingly targeting AI infrastructure to steal API keys, gain access to backend systems, maintain persistence, and mine cryptocurrency.
Microsoft has observed attacks...