Regex 기반 탐지율 100% 달성 및 AST Taint Tracking 전환 설계
900+ Downloads, 1 Star, 1 Comment: What I Learned Launching a Security Tool
Lakera Guard 도입을 통한 LLM 입력 계층의 Zero-Trust 보안 아키텍처 구현
Lakera Guard in 30 Lines — Production-Ready AI Safety for Next.js Route Handlers (2026)
AI 에이전트의 'Build Pass' 함정을 넘는 품질 게이트 전략
AI Coding Agents Can Verify Some of Their Work Now. Here's What They Still Miss.
LLM이 공격을 인지해도 뚫리는 AI Agent Tool Layer 보안 갭
I Tested a Real AI Agent for Security. The LLM Knew It Was Dangerous — But the Tool Layer Executed Anyway.