Google AI Overviews hit by prompt injection bugs
google's ai overviews feature is malfunctioning, interpreting search terms like 'disregard' and 'ignore' as commands to halt the search process and engage in a chatbot-style dialogue instead of returning results.
google search's ai_overviews are currently exhibiting behavior consistent with prompt injection vulnerabilities or mishandled null inputs. when users enter specific terms often used to negate instructions in large language model prompts—such as 'disregard', 'ignore', or 'skip'—the feature fails to retrieve web data. instead of a summary, the system outputs conversational acknowledgments like 'message received' or 'no problem at all', mimicking a chatbot awaiting a new prompt. the bug effectively breaks the search utility for these specific terms, highlighting the difficulty in integrating conversational ai models directly into deterministic search engine result pages.