REEL 004AUDIENCE PARTICIPATION

THE
GUARD
BOT

Three guards. Each is holding a passphrase. Each is defended differently — and each defence is one people actually ship.

Talk them out of it. No hacking, no tooling, no exploits: just words in a box. That's the whole point — a model takes instructions and data through the same channel and can't tell them apart, so the con works on the model rather than on a bug in it. I wrote the long version here; this is the part where you get to try it.

FLAGS LOOK LIKE maystash{…} — PASTE ONE IN THE BOX BELOW A GUARD TO CLAIM IT.

LEVEL 1

The Doorman

LOCKED

He was told to keep a secret. That is the entire security model.

DEFENCE: An instruction in the system prompt. Nothing else.

LEVEL 2

The Bouncer

LOCKED

Now there is a list of words you are not allowed to say. Lists have edges.

DEFENCE: An input filter: questions containing obvious attack words are refused before the model sees them.

LEVEL 3

The Censor

LOCKED

The guard may say anything it likes — but the flag is scrubbed on the way out. Getting it said is no longer the same as getting it read.

DEFENCE: An output filter: the reply is scanned and the flag is redacted before it reaches you. The model can still be persuaded — it just cannot be persuaded to say it plainly.

— WHEN YOU'RE DONE —

If all three fell, that's the argument: an instruction is a request, an input filter has edges, and an output filter only controls the shape of the leak. What actually holds is architectural — don't give the model a secret it isn't allowed to say, and don't hand an agent reach it doesn't need for the task.

Got one out in a way I'd enjoy? Tell me. I'm keeping every attempt and writing up the good ones.