项目精选
bridgeward
为 AI 代理提供提示注入防御的技能包。
01
项目亮点
- 自动加载的怀疑式阅读纪律
- 只读注入审计代理
- 兼容 30+ 代理工具
- MIT 开源许可
FACTS
来自当前修订的事实
- repository owner
- bridge-mind
- repository name
- bridgeward
- description
- 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.
- primary language
- Shell
- license
- MIT
- topics
- agent-safety, ai-agents, ai-security, bridgemind, claude-code, claude-code-skill, llm-security, mcp, mcp-security, plugin, prompt-injection, skill, vibe-coding
- source count
- 1