Apps & Tools
GPT-Red
An internal automated red teamer for discovering prompt injection vulnerabilities
byOpenAI
GPT-Red media is blocked
Allow external media to connect to the provider and play this content.
Description
GPT-Red is an automated system designed to find prompt injection vulnerabilities at scale using adversarial self-play. By training models against this red teamer, OpenAI significantly improves the robustness and resilience of systems like GPT-5.6 Sol against unseen attacks.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.