Create custom adversarial attack scenarios for AI agent red-teaming. Supports prompt injection, jailbreak, data extraction, social engineering, emotional manipulation, and role confusion attacks. Use when the user wants to design a specific attack test.
Create custom adversarial attack scenarios for AI agent red-teaming. Supports prompt injection, jailbreak, data extraction, social engineering, emotional manipulation, and role confusion attacks. Use when the user wants to design a specific attack test.