"ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface"

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. 출처: [The Hacker News](https://thehackernews.com/2026/05/chatgphish-vulnerability-turns-chatgpt.html)