OpenAI confirms Astra reaches Critical cyber capability and restricts access

Why it moved the index

This is OpenAI's first confirmed Critical cyber-capability designation, replacing its earlier uncertainty with direct evaluation evidence that Astra can discover unknown flaws and develop exploits across hardened systems with little human guidance. The internal evaluations include two V8 zero-days, a browser-sandbox escape, host command execution, and privilege escalation. The evidence is controlled and does not show a real-world compromise. Restricted access, a 91.5 percent cyber-refusal result, chain-of-thought monitoring, and no unauthorized-action attempts in the reported honeypot simulations materially reduce deployment and control risk, but do not erase the step change in dual-use capability.