mcp-safeguard-skill

Scan Model Context Protocol (MCP) servers for security vulnerabilities with the MCP-Safeguard CLI (@mcp-safeguard/cli). Use this when the user wants to audit or scan an MCP server/tool for security risks, triage or explain scan findings, fix MCP security issues (tool poisoning, rug-pull, cross-server shadowing, prompt injection, credential passthrough, command injection, secrets, SSRF, path traversal, excessive agency, context overshare), produce SARIF/JSON/HTML reports, or add MCP security scanning to CI / GitHub Actions. This skill drives the existing published CLI — it never reimplements the scanner.