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

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

OpenAI patched a ChatGPT security flaw that could have allowed hackers to extract Gmail data from its users, according to ...

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 ...

Security researchers used ChatGPT to secretly extract sensitive data from Gmail accounts, highlighting new risks associated with AI agents.

New ShadowLeak exploit directs ChatGPT’s Deep Research agent to exfiltrate sensitive customer data autonomously, from OpenAI serversMAHWAH, N.J., Sept. 18, 2025 (GLOBE NEWSWIRE) -- Radware® (NASDAQ: ...

A security vulnerability in OpenAI's ChatGPT Deep Research agent could have allowed unauthorized access to users' Gmail data.

The page you were looking for appears to have moved or never existed. Try searching for what you're looking for or browse ...

OpenAI has patched a security flaw in ChatGPT’s Deep Research tool that could have exposed sensitive Gmail data. Here's what ...

OpenAI has announced that it will be partnering with the US General Services Administration (GSA) to offer ChatGPT Enterprise ...