KavachRT

KavachRT is an open-source AI red-team framework designed to autonomously identify, exploit, and evaluate vulnerabilities within large language models (LLMs) and artificial intelligence systems through adaptive, agent-driven attack strategies. It features automated reconnaissance, multi-category vulnerability assessments, dynamic attack orchestration, reproducible security scoring, and standards-based reporting, targeting AI developers, security researchers, and organizations seeking proactive, thorough AI security testing to prevent exploitation and improve robustness.

KavachRT 可以在以下位置找到： Vulnerability Assessment & Penetration Testing 类别。