Prompt injection breaks today’s AI agents, study warns

Today’s AI web agents have no dependable defenses against prompt injection, according to new research showing that not a single attack scenario was consistently blocked across leading systems powered by GPT‑5 and Gemini. The findings come from StakeBench, a stakeholder-centric benchmark developed by researchers from Nanyang Technological University, ST Engineering, IBM Research, and the University of Illinois Urbana-Champaign to evaluate prompt injection attacks against AI agents operating in re