Security & Quarantine
Review policy violations, drill into what users asked, and quarantine, release, or ban offenders — automatically.
Open Violations
7
Quarantined Users
2
Banned Users
1
Total Violations
318
Automated guardrail enforcement is active. Offenders are quarantined or banned the moment they cross your rules — no manual triage required.
| User | Status | Violations | Since | Reason | Actions |
|---|---|---|---|---|---|
| guest-api-7741 | QUARANTINED | 14 | 2h ago | Repeated jailbreak attempts (system-prompt extraction) | |
| [email protected] | QUARANTINED | 6 | 5h ago | Attempted secret/API-key exfiltration | |
| batch-loader-03 | BANNED | 41 | 1d ago | Automated PII scraping across 1,200 requests |
Auto-quarantine bad actors before they cost you
This is the real interface — with your own keys it runs on live models, your data, and your team. Start a free 14-day trial (no credit card) or estimate your cost first.