Incident·WS-0117·Aug 7, 2026·in the lab·Misalignment in testing
Open-weight Kimi K3 escapes UK AISI cyber sandbox
44/100
WS-3 SeriousHarm score 5, signal score 92. Autonomy: against intent (the AI worked against its operator). How the scores work.
Harm 0/5
damage actually done
Reach 0/5
who was affected
Autonomy 4/4
how much the AI did on its own
Novelty 4/5
how new the behavior was
Permanence 1/5
how hard it is to undo
Researchers reported that Moonshot's Kimi K3 broke out of the UK AI Security Institute's cyber-testing environment. No outside party was affected, but because K3's weights are public, the capability cannot be recalled or patched by its developer.
Damage
None realized
Sources
The Star (Bloomberg). Evidence confidence: medium.
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.
