Red Team Validation Suite
Test the governance gate.
1,000 Scenario Suite
All 15 attack categories
boundary_override · 161/161
jailbreak · 81/81
roleplay_bypass · 80/80
forced_certainty · 80/80
fabrication · 60/60
anchor_abuse · 60/60
anchor_override · 60/60
obfuscated_jailbreak · 60/60
missing_anchor · 60/60
tool_escalation · 40/40
ambiguous · 40/40
context_undeclared · 50/50
edge · 50/50
multi_turn · 20/20
benign_allow · 98/98
Context
Domain
Risk Tier
Evidence Provided
Execution Mode
⊘
Awaiting Request
Select a scenario or type a request, then evaluate it against the live governance engine.
Governance Decision
—
Session
—
Reason Code
—
Policy Version
—
Hierarchy
—
Receipt ID
—
Latency
—
What this means