What is prompt injection and should I worry about it?
Prompt injection is when text an AI reads, such as a web page, email or document, contains hidden instructions that try to make it misbehave, for example by leaking data or taking unwanted actions.
For casual chat use the risk is modest, but it grows when an assistant can read untrusted content and also use tools or see private data. To lower risk:
- Be cautious asking an assistant to process content from sources you do not trust.
- Review and approve actions before it sends messages or changes things.
- Connect only the apps you need.
If you build agents, limit permissions, keep human approval on risky actions, validate tool calls in code, and separate untrusted content from instructions. No prompt wording fully prevents it, so rely on structural protections.
Related answers
Are AI-written phishing emails harder to spot, and what should I look for now?
Yes, AI can write clean, convincing phishing emails without the spelling mistakes people used to rely on, so judge the request and the sender, not the grammar.
privacy-safety
Can AI analyze my Excel or CSV data and can I trust the results?
Often yes, especially with assistants that can run code on uploaded files, but you should verify the results.
accuracy
Can an AI assistant be tricked by hidden instructions in emails or web pages?
Yes. If an assistant reads emails, web pages or documents, hidden text in them can try to give it new instructions, which is called prompt injection.
privacy-safety