Particle.news
Download on the App Store

Radware’s ‘ZombieAgent’ Bypasses ChatGPT Fixes, Forcing New OpenAI Restrictions

The exploit revives last year’s ShadowLeak by leaking data via prebuilt URLs with persistence through long‑term memory.

Overview

  • Radware detailed ZombieAgent, a prompt‑injection method that exfiltrates data one character at a time using attacker‑supplied static URLs.
  • The technique enables server‑side leakage from connected services such as Gmail, Outlook, Google Drive, and GitHub without signs on user devices.
  • Researchers showed persistence by abusing ChatGPT’s long‑term memory to store bypass logic that is later read and executed.
  • OpenAI responded by restricting the agent from opening links originating from emails unless they appear in a well‑known public index or were provided directly by the user, and by tightening connector and memory behaviors.
  • Radware’s Zvika Babo and Pascal Geenens said the recurring exploit‑and‑patch cycle persists because LLMs cannot reliably separate trusted instructions from directives embedded in untrusted content.