Radware says flaw enabled hidden email prompts to trick Deep Research agent into exfiltrating sensitive data ChatGPT's ...

“This is the quintessential zero-click attack,” said David Aviv, chief technology officer at Radware. “There is no user action required, no visible cue and no way for victims to know their data has ...

Radware has created a zero-click indirect prompt injection technique that could bypass ChatGPT to trick OpenAI servers into ...

The attack, dubbed ShadowLeak, targeted ChatGPT’s Deep Research capability, which is designed to conduct multi-step research ...

ShadowLeak zero-click flaw in ChatGPT Deep Research leaks Gmail data via hidden HTML prompts, bypassing security ...

Researchers at Radware found a zero-click flaw in ChatGPT Deep Research agent when connected to Gmail and browsing ...

Today’s installment hits OpenAI’s Deep Research agent. Researchers recently devised an attack that plucked confidential information out of a user’s Gmail inbox and sent it to an attacker-controlled ...