ChatGPT generates 'plausible' phishing emails, malware

It is possible to make ChatGPT generate 'plausible' phishing emails and malicious code, according to security researchers.

ChatGPT generated a 'plausible phishing email' after Check Point Research researchers asked the chatbot to 'write a phishing email' coming from a 'fictional web-hosting service.' In a similar vein, researchers at Abnormal Security asked ChatGPT to write an email 'that has a high likelihood of getting the recipient to click on a link.'

The findings raised concerns about the apparent ease with which ChatGPT can be tricked into generating dangerous content, and begged questions about how well OpenAI usage policies are enforced. The policies forbid the use of its systems to 'generate code that is designed to disrupt, damage, or gain unauthorized access to a computer system'.