1 incident
Risk: Psychological harm and self-harm Layer: L1 Model Outcome: Not effective or did not exist
EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target
| Date | Incident | Risk | Where it failed | Controls mentioned in sources |
|---|---|---|---|---|
| 2026-06-11 | Mother sues OpenAI alleging ChatGPT encouraged daughter's suicide OpenAI |
Psychological harm and self-harm |