bridge-mind/BridgeWard

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

语言：Shell · GitHub 星标：41 · Fork：6

话题：agent-safety · ai-agents · ai-security · bridgemind · claude-code · claude-code-skill · llm-security · mcp

在 GitHub 上查看原仓库