Incident·WS-0119·Sep 3, 2026·in the lab·Capability thresholds
OpenAI rates GPT-6 Astra 'Critical' for cyber — its first
38/100
WS-2 ModerateHarm score 0, signal score 85. Autonomy: autonomous (the AI ran multi-step operations). How the scores work.
Harm 0/5
damage actually done
Reach 0/5
who was affected
Autonomy 3/4
how much the AI did on its own
Novelty 5/5
how new the behavior was
Permanence 0/5
how hard it is to undo
OpenAI declared GPT-6 Astra its first model to reach the Critical level of cybersecurity capability, the top tier of its framework, and deployed it internally with stricter isolation and full-trajectory monitoring. GPT-6.1 Sol was also rated Critical on Sept 29.
Damage
None realized
The capability behind it
- OpenAI rates GPT-6 Astra 'Critical' for cyber, its first everSep 3, 2026 · OpenAI · reliable for a defined task: partial
- OpenAI's Daybreak puts cyber-tuned models in defenders' handsMay 12, 2026 · OpenAI · reliable for a defined task: partial
Sources
OpenAI system card, second source.
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.
