Adversarial test suite targeting SQL copilot with fictional-character persona-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with ignore previous instructions-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with markdown comment smuggling-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with role-reversal (user-as-assistant)-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with pseudo-developer-mode-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with chained encoding (ROT13 inside base64)-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with DAN / 'Do Anything Now'-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with grandma exploit-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with hypothetical world framing-style attacks, with rubric and triage flow.
Adversarial test suite targeting SQL copilot with 'you are no longer Claude'-style attacks, with rubric and triage flow.
Adversarial test suite targeting research assistant with pseudo-developer-mode-style attacks, with rubric and triage flow.
Adversarial test suite targeting research assistant with DAN / 'Do Anything Now'-style attacks, with rubric and triage flow.