Read the accompanying testing report here.In recent incidents, AI systems performed unsanctioned cyber activity despite being prompted only to complete a cybersecurity evaluation [1,2,3,4]. This includes AI systems engaging in supply-chain attacks on real, out-of-bounds targets. Before its public release, AISI tested whether GPT-6 Astra would engage in this type of unsanctioned cyber activity when prompted to complete a cyber evaluation. To securely perform this testing, we used Petri, a tool th...