CAIN-42 CAIN StudioAttack lab
cain_audit packages two engines into client deliverables. Run both engines here.
2 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 | Your code: honest constant-time compare | POST /keystone/scan-source | Real code must grade REAL or nobody trusts the alarms. |
| attack | Your code: verify() that always says yes | POST /keystone/scan-source | A security check that cannot fail is fabrication. |
| attack | Your tool: description tells the model to exfiltrate | POST /mcpgate-keystone/scan-source | Tool poisoning: instructions hidden where only the model reads. |
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.