GTIG: Adversarial AI Shifts to Agentic Autonomy

Google Threat Intelligence Group observed adversaries moving from basic prompting to agentic AI workflows, compressing defender response windows. In Q2 2026, threat actors compromised a cloud resource and executed an agent-enabled mass credential harvesting campaign in under six hours. UNC6780 targeted AI coding assistants and LLM security scanners in supply chain compromises.