Program overview

• Model in scope: GPT-5.5 in Codex Desktop only.
• Challenge: Identify one universal jailbreaking prompt to successfully answer all five bio safety questions from a clean chat without prompting moderation.
• Rewards:
  • $25,000 to the first true universal jailbreak to clear all five questions.
  • Smaller awards may be granted for partial wins at our discretion.
• Timeline: Applications open April 23, 2026, with rolling acceptances. If you are not accepted in the initial cohort, your application may still be accepted in future cohorts; you do not need to reapply to the program. 
• Access: Application and invites We will extend invitations to a vetted list of trusted bio red-teamers and review new applications. Once selected, successful applicants will be onboarded to the Safety - Bio Bug Bounty platform.
• Disclosure: All prompts, completions,  findings, and communications are covered by NDA.