URL has been copied successfully!
New attack on ChatGPT research agent pilfers secrets from Gmail inboxes
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

New attack on ChatGPT research agent pilfers secrets from Gmail inboxes


Tags: , , , ,

Unlike most prompt injections, ShadowLeak executes on OpenAI’s cloud-based infrastructure.

First seen on arstechnica.com

Jump to article: arstechnica.com/information-technology/2025/09/new-attack-on-chatgpt-research-agent-pilfers-secrets-from-gmail-inboxes/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. Gen AI is transforming the cyber threat landscape by democratizing vulnerability hunting
  2. We’re losing”Š”, “Šbut it can’t get any worse, right?
  3. ChatGPT API flaws could allow DDoS, prompt injection attacks
  4. ChatGPT Operator Prompt Injection Exploit Leaks Private Data