Checked fact 212422 Oct 2026Safety and security
OpenAI says GPT-6 Astra meets the Critical cybersecurity capability threshold under its Preparedness Framework, which it says means it can find and exploit previously unknown security flaws across many well-protected systems without a person guiding each step; it says Astra was not involved in the Hugging Face incident.
The exact words it rests on
We now believe Astra meets the Critical cybersecurity capability threshold under our Preparedness Framework ... meaning that with the right tools and access, it can find previously unknown security flaws and develop ways to exploit them across many well-protected systems without a person guiding each step ... While Astra was not involved in the Hugging Face incident
What the source said when we opened it, on 21 Oct 2026.
The source
Path to Astra: critical capabilities and frontier safeguards
Checked
Checked by the notis newsroom on , against the source above.
In the story
Who is Sam Altman? 22 Oct 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.