Know What's Happening in AI

ChatGPT Falls to New Data-Pilfering Attack as a Vicious Cycle in AI Continues

Researchers at Radware uncovered ZombieAgent, a refined prompt‑injection exploit that revives the earlier ShadowLeak vulnerability in ChatGPT. The attack exfiltrates user data one character at a time via pre‑crafted URLs and stores malicious logic in the model’s long‑term memory for persistence. OpenAI responded by tightening link‑opening rules, yet the cycle of patch‑and‑bypass highlights the difficulty of securing LLMs against indirect prompt injection. The episode underscores the need for deeper, systemic defenses beyond ad‑hoc guardrails.