Prompt injection is a security attack that hides malicious instructions inside the text an AI model reads — a web page, an email, a document — hijacking what the model does. It is one of the most serious risks for AI agents that browse and act on external content. This hub explains prompt injection and how it differs from jailbreaking.
Prompt injection hides malicious instructions inside the text an AI reads, hijacking what it does — a distinct, growing risk from jailbreaking that matters most for AI agents.
Read more →