MCP 기반 AI Agent의 신뢰 모델 전환 및 Zero Trust 거버넌스 설계
MCP Security: The Risks of Model Context Protocol and How to Govern It (2026)
MCP Security: The Risks of Model Context Protocol and How to Govern It (2026)
You Wanted Me to Delete the DB, Right?
Google told researcher 'Nice catch!' Then denied bug bounty for flaw it still hasn't fixed
AI agents are a confused deputy with the keys to your kingdom
AI agents expose the security checks you never actually wrote
webMCP Isn't the New Accessibility Layer—It's a New Attack Surface: A governance-grade reframing of a playful demo
Email is the largest untrusted-input surface an agent has
RedSun turned Defender into a write primitive
The Missing bandit for AI Agents: How I Built a Static Analyzer for Prompt Injection
Autonomous AI Agents Attack Surface 2026 — Security Risks of Agentic AI
The Confused Deputy Problem Just Hit AI Agents — And Nobody's Scanning for It