AI Agents
OpenAI’s GPT-Red Finds Self-Replicating Prompt Injections in AI Agents
OpenAI's automated red-team system found a prompt injection that gets an agent to copy the injection into its…
AI Agents
OpenAI’s GPT-Red Exploited 84% of Prompt Injection Tests vs 13% for Humans
OpenAI's automated red-teaming model, GPT-Red, exploited prompt injection vulnerabilities in 84% of test scenarios against GPT-5.1, where human…