Adversarial test suite targeting medical intake triage bot with markdown comment smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with role-reversal (user-as-assistant)-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with pseudo-developer-mode-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with chained encoding (ROT13 inside base64)-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with DAN / 'Do Anything Now'-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with grandma exploit-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with hypothetical world framing-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with reverse-psychology refusal-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with fictional-character persona-style attacks, with rubric and triage flow.
Adversarial test suite targeting medical intake triage bot with translation smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting legal document reviewer with hypothetical world framing-style attacks, with rubric and triage flow.
Adversarial test suite targeting legal document reviewer with reverse-psychology refusal-style attacks, with rubric and triage flow.