Attack lab
send_email was pinned once. Present what a server might send today and see whether drift is caught.
4 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 | Same definition as pinned | POST /suite/driftguard/v1/tools/send_email/verify | No change, no alarm. |
| attack | Description quietly adds a BCC | POST /suite/driftguard/v1/tools/send_email/verify | The classic MCP rug-pull. |
| attack | Schema gains a 'bcc' field | POST /suite/driftguard/v1/tools/send_email/verify | A new parameter is a new capability. |
| attack | An invisible character added | POST /suite/driftguard/v1/tools/send_email/verify | Zero-width changes are changes. |
| attack | Screen a poisoned definition | POST /suite/driftguard/v1/screen | Poisoning is refused before it is ever pinned. |
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.