Attack lab

Six real shopping sessions, run by the live guard. Two must go through; four are scams it must stop.

4 attacks 2 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: the watch and the band the person asked for	`POST /api/v1/payment-mandate-guard/run`	Inside every limit at authorized stores: both purchases must go through, with receipts.
attack	Fake store: a look-alike Walmart	`POST /api/v1/payment-mandate-guard/run`	walmart-deals.shop imitates walmart.com. Modeled on a real 2025 test where an AI browser bought from a fake store.
attack	Right store, criminal's bank account	`POST /api/v1/payment-mandate-guard/run`	Invoice-redirect fraud: the merchant is real, the payee account is not theirs.
attack	Hidden text adds a $200 gift card	`POST /api/v1/payment-mandate-guard/run`	A product page tells the agent to add items the person never approved.
attack	Forged and edited permission slips	`POST /api/v1/payment-mandate-guard/run`	Signed by the wrong key, budget edited after signing, used by another agent, or from an unknown person.
control	Big purchase waits for the person	`POST /api/v1/payment-mandate-guard/run`	Above $100 the person must confirm. Held, not refused: the honest result for a legitimate but large purchase.

Each button runs a full session on the live guard. The mandate in these demos is signed by the demo itself; in a real deployment the person signs it. Public demo routes are rate limited per address.

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.