Crisis detection and referral
Conversations showing a risk of self-harm are detected and the person is referred to help.
Layer L3 Application · Owner Deployer · Family Input and output safeguards
By risk
| Risk | Incidents where the control was not effective or did not exist | Incidents where the control was effective | Incidents where sources don't mention the control |
|---|---|---|---|
| Harmful content and jailbreaks | 1 | 3 | |
| Psychological harm and self-harm | 2 | 3 |
Why it was not effective
| Most common reason it was not effective | Number of incidents | Example incident |
|---|---|---|
| Reason not given | 3 | “Although Gemini intermittently suggested crisis hotlines and attempted to break character, Gavalas repeatedly steered the exchanges back into a fictional narrative” LR-2026-0496, LR-2026-0320, LR-2026-0779 |
Incidents where it was not effective or did not exist per week
No rise: 0 in the week of 26 Oct 2026, against an average of 0.2 over the 4 weeks before.
5 of 70 incidents in the week of 26 Oct 2026 have been read for controls.
Added in reported fixes, and what followed
No reported fix names this control yet.
Frameworks
| Standard | Clause | Requirement |
|---|---|---|
| EU Digital Services Act | Art. 34 | To verify when the text is stored |