CyberStrikeAI Uses 44 AI Agents to Automate Hacking Operations Against Japan Targets

Cybersecurity researchers at TrendAI have disclosed three cyber attacks targeting organisations in Japan in which AI was either driving the operation or assisting a human operator. In the first, the open-source CyberStrikeAI penetration-testing tool delegated work among 44 agents to automate reconnaissance, exploitation, command-and-control, persistence and exfiltration, and at least 19 identifiable organisations, including at least 16 in Japan, were subjected to validation activity; the other cases involved an LLM-assisted operator stealing records from a GIS server exposed with default credentials, and AI used only to develop an operator’s tools against edge devices.