cc-safety-net
AI编码代理护栏——一个CLI钩子，在执行前阻止破坏性的git和文件系统命令以及秘密文件访问。支持Amp Code、Antigravity CLI、Claude Code、Codex、Copilot CLI、Cursor、Gemini CLI、Hermes Agent、Kimi Code、OpenClaw、OpenCode和Pi。
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
怎么安装
git clone https://github.com/kenryu42/claude-code-safety-net ~/.claude/skills/claude-code-safety-net npx -y cc-safety-net 简介
**English** · 简体中文 · 日本語 CC Safety Net — short for **Coding CLI** Safety Net — is a PreToolUse hook that blocks destructive commands and access to secrets like SSH keys and .env files, before AI coding agents run them. It parses command **semantics**, so flag reordering, shell wrappers, and interpreter one-liners can't bypass it. [!NOTE] **Full documentation →** — installation, configuration, reference, guides, and the security model live on the docs site. This README is the short version. Why this exists We learned the hard way that instructions aren't enough to keep AI agents in check. After…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 1.6K
- 月下载
- 25.2K
- 最近更新
- 2026-09-24
- 创建于
- 2025-12-25
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:hesreallyhim/awesome-claude-code
- 主题标签
- ai-agents, ai-safety, antigravity, claude, claude-code, claude-code-plugin, cli, codex, codex-cli, coding-agent, cursor, developer-tools, gemini-cli, guardrails, hermes-agent, hooks, openclaw, opencode, pi-extension, security
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