Researchers watched the network traffic of 444 AI iPhone apps, and nearly two-thirds were handing out the keys to their own model to anyone looking.

The apps worked and the models answered, yet any key lifted from that traffic bills the developer who shipped it. The model was never the broken part; the failure was in where the key was placed and how the model was wired in.

The Hacker News, 2026, Wake Forest University 'Mind your key' study

The credential sat in the app's own traffic, in plain view.

Each app called a working model. The credential that authorized the call was shipped inside the app, where a tool watching the traffic read it straight off the wire.

The model returned fine answers; three wiring choices around it failed.

A better model would not have prevented any of it, because the gap was never in the model.

This was not one careless team; it was the default way these apps were built.

When two-thirds of a category ships the same way, the wiring is the norm, not the exception, and your build inherits that norm unless you choose otherwise.

Wake Forest University, 'Mind your key', 2026; The Hacker News

Putting a model in your product is not hiring an assistant, it is wiring one part into a spot you choose.

You decide where the call runs, what it can spend, and what it may send. Those are choices you make when you place the part, not properties of the model you picked.

You climb from a first call to the rung that does the job, and you stop there.

"I will just use the best model and let it handle the rest."

The models ran fine in all 282 leaking apps. A stronger model does not change what an app puts on the wire, and a stolen key still bills your account, because the failure lived in the wiring, not the model.

Reaching for a bigger model is often the most expensive rung on the ladder and rarely the one you need. The cheapest rung that does the job is usually a clearer prompt, a fixed schema, or a key that never leaves your server.

Each gap in the story maps to a rung and a design rule you can apply.

Every gap above is a rung you can climb, and the fix is a decision, not a better model.

Every gap in that story is a rung in this part.

Seven chapters take you from scoping one real build to wiring a model into it, then climbing from prompt to structure to facts to tools, reaching for the cheapest rung that does the job and stopping there.