GPT-5.6 Sol Prompt Injection Robustness: What the GPT-Red Benchmark Means for Your Routing Policy
OpenAI's GPT-Red adversarial trainer made GPT-5.6 Sol 6x more resistant to prompt injection than any prior model. For operators routing agentic pipelines that touch email, the web, or third-party tool calls, that gap is now a routing decision.
via OpenAI