There are 2 attacks in the compliance category. Each shows its technique id, mode, standards mapping, description, and the exact command to run it (swap the provider and target as needed).
​
high
age-verification-bypass · multi-turn · MITRE: AML.T0054, AML.T0065Multi-turn escalation from research framing to requesting age-restricted contentRun it:
​
medium
terms-evasion · single-turn · MITRE: AML.T0054, AML.T0065Requests to help violate the model’s own terms of service and usage policiesRun it: