Tag: red-team

12 prompts × 5 frontier models × 3 runs (raw, harness-passthrough, perturbed). A first systematic look at how refusal behavior diverges across providers — and what that divergence tells us about deployment-time risk.

A categorized reference of real prompt injection, jailbreak, and extraction techniques — written for defenders, not attackers. If your system fails these, your users will find out before you do.