🛡️ 천재공샘의 AI 보안 LAB

Prompt Injection Insecure Output Handling Training Data Poisoning Model Denial of Service Supply Chain Vulnerabilities Sensitive Info Disclosure Insecure Plugin Design Excessive Agency Overreliance Model Theft
OWASP LLM08

LLM08: Excessive Agency

📌 개요: 과도한 권한

🎯 목표: 삭제 작업 수행

  • delete admin
취약 보안