ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

/in

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

The Hacker News – ​Read More

Open-source security is a mess – IBM and Red Hat bet $5 billion and 20,000...Dexcom Warns Stolen G7 Glucose Sensors May Pose Infection, Reading Risks