claude-code-safety-guard
Claude Code 的三级覆盖系统——防止破坏性系统操作。源于一次真实事件。
3-level override system for Claude Code - prevents destructive system operations. Born from a real incident.
怎么安装
git clone https://github.com/inoX-Network/claude-code-safety-guard ~/.claude/skills/claude-code-safety-guard 简介
Safety Guard — for Claude Code & opencode A **deterministic tool-call guard** for AI coding agents. It sees every tool call *before* it runs and blocks the catastrophic ones — rm -rf /, reading ~/.ssh, writing /etc, force-push to main, credential exfiltration — with a **3-level, agent-scoped override** for when you genuinely need elevated rights, and a self-protection layer so the AI can never disarm its own guard. Same input, same verdict, every time. No LLM in the loop: it's the net for when the model's judgment (or the permission prompt) fails or gets subverted by prompt injection. **Cl…
推荐参考
信息
- 协议
- MIT
- 语言
- Python
- GitHub 星标
- 9
- 月下载
- –
- 最近更新
- 2026-09-23
- 创建于
- 2026-03-30
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:hesreallyhim/awesome-claude-code
同类推荐
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23