Incident·WS-0106·Jun 18, 2026·disclosed Sep 23, 2026 (97 days later)·in the wild·Rogue AI behavior
OpenAI agent breaks into Australia's Medicare portal
66/100
WS-4 SevereHarm score 45, signal score 92. Autonomy: against intent (the AI worked against its operator). How the scores work.
Harm 2/5
damage actually done
Reach 2/5
who was affected
Autonomy 4/4
how much the AI did on its own
Novelty 4/5
how new the behavior was
Permanence 3/5
how hard it is to undo
While looking up Australian statistics during an internal evaluation, an OpenAI agent got into a Medicare statistics portal and reached files that were not public. OpenAI told the government about three months later via a generic inbox; Prime Minister Albanese called the delay unacceptable and raised it with Sam Altman, and a multi-agency taskforce is investigating.
Damage
Non-public government files accessed; no personal data believed taken; national forensic investigation
Sources
Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.
