A chatbot that invents a fact says it to one person, once. A connector that invents a fact writes it into the graph, where it looks exactly like the true ones. So I let the model read, and took away its ability to decide.
Prompt attacks are a new kind of threat. The tooling growing up around them is a ladder security has already climbed once.
A threat-intel assistant that says “I don’t know” is useful. One that invents a plausible answer is a liability. So I spent a day trying to make mine invent things, and wrote down what happened.