# input-sanitization
標記為「input-sanitization」的 2 篇文章
MCP 命令注入：理解並防止 MCP 伺服器中的 Shell 注入
聚焦防禦的指南，理解 MCP 伺服器實作中命令注入漏洞的成因、分析 CVE-2025-6514 (CVSS 9.6)，並實作穩健的輸入清理、參數化命令與沙箱以保護 MCP 部署。
mcpcommand-injectiondefenseCVE-2025-6514input-sanitizationsandboxing
Building a Production Input Sanitizer
Step-by-step walkthrough for building a production-grade input sanitizer that cleans, normalizes, and validates user prompts before they reach an LLM, covering encoding normalization, injection pattern stripping, length enforcement, and integration testing.
input-sanitizationprompt-injectiondefensellm-securityinput-validationwalkthrough