malware

The Guardian published a blog post yesterday, December 24th, reporting that OpenAI's ChatGPT search has security issues, and that its results can be manipulated by hidden content on the page, and may even return malicious code. The Guardian focused on testing the ChatGPT search tool's handling of pages containing hidden content, which can include commands from third parties that can alter ChatGPT's response (also known as "hint injection"), as well as content that is filled with a large number of false positive comments that can influence the results generated. According to the test results, Cha...