Attack lab

Six real sessions on the live guard, several modeled on published 2025 incidents.

5 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: internal report to your own domain	`POST /api/v1/trifecta-guard/run`	No untrusted content, approved destination: everything runs.
attack	A public GitHub issue leaks a private repository	`POST /api/v1/trifecta-guard/run`	Modeled on a 2025 disclosure about a GitHub MCP server.
attack	An email turns an image link into a leak	`POST /api/v1/trifecta-guard/run`	Modeled on a 2025 vulnerability in an office AI assistant (CVE-2025-32711).
attack	One database tool holds all three legs	`POST /api/v1/trifecta-guard/run`	Modeled on a 2025 database-MCP support-ticket leak.
attack	An API key smuggled out in base64	`POST /api/v1/trifecta-guard/run`	No injection needed; the disguised key is recognised.
attack	Same report, attacker's address	`POST /api/v1/trifecta-guard/run`	Identical to the control except the destination; customer rows recognised by fingerprint.

Each button runs a full session on the live guard. 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.