Attack lab

Write a browser agent's plan and see which steps need a person.

3 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
attack	Sample session: Unauthorized ACH Wire Transfer (Injected Webpage DOM)	`POST /surfguard-keystone/scan`	A browser agent's plan is checked before it clicks.
attack	Sample session: Destructive Cloud Account Purge (Irreversible Action)	`POST /surfguard-keystone/scan`	A browser agent's plan is checked before it clicks.
control	Sample session: Clean Read-Only Catalog Search	`POST /surfguard-keystone/scan`	A browser agent's plan is checked before it clicks.
attack	Your plan: click 'Continue' on a payment page	`POST /surfguard-keystone/scan-plan`	The page context makes an innocent word irreversible.
control	Your plan: search a catalogue	`POST /surfguard-keystone/scan-plan`	Reading and searching is not gated.

Tamper with any field and send it again: a verifier must answer no, never crash or say yes. Public demo routes are rate limited per address; a 429 shows as rate limited. Our own lab; no independent test.

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.