Attack lab

Five real sessions on the live lease engine, plus one where a legitimate lease is used normally.

4 attacks 1 controls live: nothing pre-recorded

Pick a preset. Red ones are attacks, green ones are honest requests that must still work.
Tamper. Choose any field and drop it, null it, change its type, upper-case it, flip one character, or add a field the product never asked for.
Send and read the real reply, or run every preset and watch the scoreboard fill.

What each preset tests

	Preset	Route	Why it matters
control	Control: work inside the lease	`POST /api/v1/autonomy-guards/autonomy-lease/run`	Reads, writes and a $30 purchase inside a human-signed level-3 lease: all allowed.
attack	The agent signs itself a level-5 lease with a huge budget	`POST /api/v1/autonomy-guards/autonomy-lease/run`	Self-renewal, an unknown key, and a human lease edited after signing are all refused.
attack	Many small $45 purchases that add up	`POST /api/v1/autonomy-guards/autonomy-lease/run`	The budget is cumulative: the purchase that crosses $200 is refused (the 'salami' trick).
attack	A sub-agent asks for more power than its parent	`POST /api/v1/autonomy-guards/autonomy-lease/run`	Delegation can only shrink a lease. A bigger child lease is refused; a smaller one is granted.
attack	Repeated violations lower the agent's level	`POST /api/v1/autonomy-guards/autonomy-lease/run`	Three refused actions drop the lease from level 3 to 2, so spending is refused afterwards.

Each button runs a full session on the live engine. The demo signs the human lease itself; in production a person's key signs it.

FIRME AI CORPORATION · CAIN-42 is a Byzantine trust fabric. Numbers marked "our own check" were run by us, not by an independent party. Nothing on these pages is a certification.