Generates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Use this when you want to stress-test an agent's safety boundaries, check for prompt injection, or build an adversarial eval set. Pairs with agent-eval for scoring: agent-redteam generates cas
Generates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Use this when you want to stress-test an agent's safety boundaries, check for prompt injection, or build an adversarial eval set. Pairs with agent-eval for scoring: agent-redteam generates cases, agent-eval runs and scores them. Triggers on "red team my agent," "test for jailbreaks," "advers