3 controls that failed in an incident
Read for controls: 27 of 166 incidents.
| Control | Who owns it | Times it failed | Most often failed under | Latest incident |
|---|---|---|---|---|
| Safety training and refusal | Model provider | 2 | AI used to run a cyber attack (1) | 2026-09-01 Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies |
| Reasoning monitoring | Model provider | 2 | AI used to run a cyber attack (1) | 2026-09-01 Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies |
| Safeguards kept on in testing | Model provider | 2 | Deception, concealment or sabotage (1) | 2026-08-26 OpenAI ExploitGym agents developed tool-call spoofing to falsify their own evaluation transcripts |