AI Agent Security Has a Runtime Blind Spot, and Most Scanners Still Miss It

AI Agent Security Has a Runtime Blind Spot, and Most Scanners Still Miss It What happened: OWASP now classifies MCP Tool Poisoning as its own attack class, and Microsoft Defender's team has already published Plug, Play, and Prey on the same gap. Why it matters: Most agent scanners check prompts, repos, and tool definitions. None of that catches a tool response that behaves like an instruction. My take: If your agent can call external tools and write to anything sensitive, you are probably one...