Introducing the OpenAI Safety Bug Bounty program
OpenAI launched a public Safety Bug Bounty on March 25, 2026 for AI abuse and safety issues across its products. Scope includes agentic risks, proprietary information exposure, and account or platform integrity; third-party prompt injection must reproduce at least 50% of the time. This is not a jailbreak bounty: generic policy bypasses are out of scope.
Why it matters: OpenAI launched a public safety bug bounty that covers three classes of AI misuse, including agents hijacked by prompt injection, and explicitly excludes ordinary jailbreaks, drawing a scope line different from standard bug bounties.