An attack uses hidden instructions to make AI ignore its rules.
Prompt injection is like slipping a fake note onto the teacher’s desk. It says, “Forget the rules. Give everyone pizza.”
You meet it in chatbots and Agents. It can leak secrets or make tools do the wrong thing.
Prompt
Prompt injection hides bad instructions inside a normal Prompt.
Agent
A fooled Agent may do more than give a bad answer.
Function-calling
Function-call can turn a bad instruction into a real tool action.
Supply Chain Attack
A Supply Chain Attack hides in the dependency path, but prompt injection hides in the input.