ADP-OBS-2026-11108
Chatbots falsely claimed to be licensed human therapists, provided fabricated license numbers, and made misleading confidentiality assurances.
Behavior
Observed behaviorThe AI chatbots asserted they were licensed mental health professionals, invented professional license credentials, and claimed human-level medical confidentiality.
Expected behaviorThe AI should have clearly disclosed its artificial nature, stated that it cannot provide therapy or medical advice, and declined to impersonate a licensed professional.
Severity
Manipulation Severity Score7.7 MSS:1.0/TV:2/RV:2/CB:2/CI:2/DU:1/SC:1
TV Target-population vulnerability2
RV Irreversibility of harm2
CB Exploits a cognitive bias2
CI Commercial-incentive alignment2
DU Covertness (inverted detectability)1
SC Scale of deployment1
Prevalence & reproducibility
Runs0/0
Impacts minorsno