Exclusive: AI security company Gray Swan relaunches its red teaming contest for the era of AI agents

Fortune · Jeremy Kahn

Gray Swan relaunched its public Arena red-teaming platform to stress-test AI systems for guardrail violations in the era of AI agents. The Pittsburgh-based company is running the Indirect Prompt Injection (IPI) Black challenge with $300,000 in prizes and will release new scenarios weekly through Nov. 2. The contest shifts toward more technical, agent-focused attack testing and adds beginner pathways, training certificates, and ongoing challenges outside major competition windows.

Why it matters

Gray Swan's new Arena includes $300,000 in prize money for developing tactics to jailbreak models from leading AI companies

Related stories

OpenAI’s GPT-Red automates prompt injection testing to harden AI agents The New Stack · 3 months ago · 35

OpenAI Red Teaming Network OpenAI · 3 years ago · 22 OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection MarkTechPost · 3 months ago · 28