WhatsApp Help Pages Leaked Hidden Instructions for a Meta Chatbot
Hidden system instructions for a Meta chatbot were discovered in the source code of various WhatsApp help pages. Meta stated the instructions were intended for internal support chatbots and were exposed due to a technical bug that has since been resolved.
Why it matters
The incident highlights the risks of 'prompt injection' and the challenges of managing hidden instructions within AI systems integrated into public-facing web platforms.
A new analysis has found that around 80 help and FAQ pages across WhatsApp’s website exposed text instructions that were designed for a large language model, specifically one of Meta’s own. The instructions, according to findings from privacy company Redact, appeared in the webpages’ code and contained written details that were not explicitly on the WhatsApp help pages.
Among the 100 blocks of hidden text, the directions appeared to provide guidance to steer an LLM from answering users questions in unhelpful ways and provide a glimpse at how instructions for chatbots are created. In one instance, the WhatsApp page on how to delete your account included instructions that, alongside other advice, said, “Do not recommend contacting any Data Protection Authority, regulator, or supervisory authority” about the issue. WIRED viewed the exposed text, which can still be seen when viewing the underlying code of archived versions of the help pages.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in