A guard-agnostic benchmark for MCP injection / exfil / tool-poisoning detection. Versioned cases + a language-agnostic runner that scores any guard through its own published CLI.
- advisory code analysis flagged committed secret ×2 in getmcpm/mcp-guardbench
- advisory code analysis flagged committed secret ×2 in getmcpm/mcp-guardbench
- advisory code analysis flagged committed secret ×2 in getmcpm/mcp-guardbench
- resurrection repo came alive getmcpm/mcp-guardbench
- new_repo new repo getmcpm/mcp-guardbench
j down k up gg top G end