AI assistants like ChatGPT, Claude and Gemini are great at summarizing long articles or PDFs, but there is a growing security threat that most users are completely ignoring. It’s called Indirect Prompt Injection, and it could allow a malicious website to hijack your AI assistant without you ever clicking a link.
The problem is, AI doesn't have a 'BS filter.' You know, the kind of common sense that makes humans hesitate when something feels..."off." When you read a website, you can tell the difference between the actual article and a spammy pop-up. But, AI cannot; to a Large Language Model (LLM), all text is created equal.
