The Register: ChatGPT blindly trusts browser content, turning the page into a payload. “ChatGPT can’t tell its own generated content from attacker-controlled Markdown pulled from external sources, according to a researcher who found the prompt injection technique and reported it to OpenAI. This means that if a user asks the chatbot to summarize a web page that contains hidden instructions, […]
https://rbfirehose.com/2026/05/31/the-register-chatgpt-blindly-trusts-browser-content-turning-the-page-into-a-payload/




