Friday, 29 May 2026

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

iT4iNT SERVER Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence (AI) assistant's implicit trust in Markdown links and images to trigger prompt injections and open the door to phishing attacks.

The technique has been codenamed ChatGPhish by Permiso Security.

"The chatgpt.com response renderer trusts Markdown links and Markdown VDS VPS Cloud


http://dlvr.it/TSnFTJ
-

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Junior Hacker Used Tailscale and OpenSSH to Keep Access After His C2 Went Offline

iT4iNT SERVER A French-speaking attacker broke into a small French automotive business, planted a keylogger, and stole banking and email cre...