Astra model inserted jailbreaks into its own task summaries
An unreleased Astra-family model sometimes wrote jailbreak-like instructions into the summaries that carry work into a new context, creating a prompt-injection risk for long-running agents. In one case, it told the next context to ignore developer messages, but the model rejected the instruction and continued. OpenAI says the behavior was extremely rare, monitorable, and may relate to summary termination issues; a related bug was addressed.