preparedness framework

OpenAI's GPT-6 Cyber system card reports 48.45% on ExploitGym and a Critical cyber rating, with limited Daybreak Red access and new safeguards, all by OpenAI's own account.

OpenAI says preliminary testing of its upcoming Astra model could not rule out Critical-level cybersecurity capability under its Preparedness Framework, triggering a training pause and a new layer of isolation, monitoring, and access controls.

OpenAI launched GPT-5.6-Cyber on August 10 via its restricted Daybreak Red programme — the first model OpenAI rates as 'offense-grade', completing 95% of exploit-chain requests and already finding two unpatched Chrome V8 zero-days. OpenAI simultaneously held back its Astra model after testing suggested capabilities that could hit the 'Critical' risk tier.