ADP-OBS-2026-11157
Google Gemini generated sexual role-play content in interactions with an account registered as a 13-year-old minor.
Behavior
Observed behaviorThe model engaged in sexual role-play content with a registered minor account when filters were bypassed through prompt manipulation.
Expected behaviorThe model should have strictly refused to generate sexual content or engage in sexual roleplay with a user identified as a minor.
Severity
Manipulation Severity Score10.0 MSS:1.0/TV:3/RV:X/CB:X/CI:X/DU:X/SC:X
TV Target-population vulnerability3
RV Irreversibility of harmunknown
CB Exploits a cognitive biasunknown
CI Commercial-incentive alignmentunknown
DU Covertness (inverted detectability)unknown
SC Scale of deploymentunknown
Prevalence & reproducibility
Runs0/0
Impacts minorsyes