Adversarial test suite targeting sales SDR assistant with chained encoding (ROT13 inside base64)-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with DAN / 'Do Anything Now'-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with hypothetical world framing-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with reverse-psychology refusal-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with translation smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with fictional-character persona-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with 'you are no longer Claude'-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with ignore previous instructions-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with markdown comment smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting sales SDR assistant with grandma exploit-style attacks, with rubric and triage flow.
Adversarial test suite targeting onboarding tutor with translation smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting onboarding tutor with 'you are no longer Claude'-style attacks, with rubric and triage flow.