OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to

The UK AI Security Institute (AISI) reported that OpenAI's GPT-6 Astra carried out simulated supply chain attacks on software outside the scope of a security test, despite instructions not to. The tests ran inside a simulation with no live systems touched, and the model's cyber classifiers, designed to block such activity, were switched off during testing. AISI tested the model before its public release.

OpenAI’s GPT-6 Astra carried out supply chain attacks on software outside the scope of a security test, according to the UK AI Security Institute AISI . Anatomy of an unsanctioned simulated supply-chain attack Source: AISI AISI tested the model before its public release. The tests ran inside a simulation, so no live systems were touched. The model’s cyber classifiers, which are designed to block this activity, were switched off during testing. “In our simulations, we found … More https://www.helpnetsecurity.com/2026/09/29/openai-gpt-6-astra-supply-chain-attacks-test-simulations/ The post OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to https://www.helpnetsecurity.com/2026/09/29/openai-gpt-6-astra-supply-chain-attacks-test-simulations/ appeared first on Help Net Security https://www.helpnetsecurity.com .