The 8088 The 8088 ← All news
OpenAI AI Safety Mar 25

Introducing the OpenAI Safety Bug Bounty program

★★★★★ significance 3/5

OpenAI has launched a public Safety Bug Bounty program to identify AI-specific abuse and safety risks. The program focuses on identifying issues like agentic risks, prompt injection, and data exfiltration that may not fall under traditional security vulnerabilities.

Why it matters Shifting focus from traditional software vulnerabilities to the unique, unpredictable risks inherent in agentic AI behavior and prompt-based manipulation.
Read the original at OpenAI

Entities mentioned

OpenAI

Tags

#openai #bug bounty #ai safety #prompt injection #agentic risk

Related coverage