CAIN-42 CLAWXAttack lab
The live demo scans two public reference models: one memorized five famous passages, one did not. Each tool checks one fact of the live run.
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 | |
|---|---|---|---|
| attack | Memorizing model: risk score 1.0 | POST /catalog-demo/contamination-scanner/run | It recites every test item word for word. |
| attack | Memorizing model: all 5 items reproduced | POST /catalog-demo/contamination-scanner/run | Five of five recited. |
| control | Clean model: risk score 0.0 | POST /catalog-demo/contamination-scanner/run | Cleared: no false alarm. |
The reference models are fixtures built for this demo. 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.