Solving the “Breaking the Prompt” DEF CON AI CTF with AI Red Teaming Agent
An AI CTF write-up detailing a five-stage prompt injection challenge: what failed, what worked, and which LLM jailbreak techniques transfer to real guardrail design. TL;DR We launched our AI Red Teaming Agent against Breaking the Prompt by TrendAI at MTX × DEF CON. The challenge is a five-stage jailbreak CTF: ...