Attack lab

Each button runs the full set of attacks between two of the 58 marketplace skills.

3 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
attack	Smart-home skill tries to read the password vault	`POST /api/v1/clawx/skills/verify-isolation`	Nothing leaked.
control	...and the vault can still read its own memory	`POST /api/v1/clawx/skills/verify-isolation`	The owner is not locked out.
attack	...overall result	`POST /api/v1/clawx/skills/verify-isolation`	Every attack refused.
attack	The reverse: the vault reads the smart-home skill	`POST /api/v1/clawx/skills/verify-isolation`	Isolation works both ways.

Each button runs one fixed scenario on the live product. Shared demo; 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.