菜单
7-layer AI security scanner for OpenClaw. Blocks prompt injection, SSRF, command injection, data leakage, and memory poisoning across ALL channels (Signal, Telegram, Discord, WhatsApp, web) simultaneously.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/javimosch/open-claw-skills --skill zugashield命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Connect your AI assistant to GoHighLevel CRM via the official API v2. Manage contacts, conversations, calendars, pipelines, invoices, payments, workflows, and 30+ endpoint groups through natural language. Includes interactive setup wizard and 100+ pre-built, safe API commands. Python 3.6+ stdlib only — zero external dependencies.
Manage Cloudflare DNS records, Tunnels (cloudflared), and Zero Trust policies. Use for pointing domains, exposing local services via tunnels, and updating ingress rules.
Mema's personal brain - SQLite metadata index for documents and Redis short-term context buffer. Use for organizing workspace knowledge paths and managing ephemeral session state.
基于 SOC 职业分类
正在显示 SKILL.md
| name | zugashield |
| description | 7-layer AI security scanner for OpenClaw. Blocks prompt injection, SSRF, command injection, data leakage, and memory poisoning across ALL channels (Signal, Telegram, Discord, WhatsApp, web) simultaneously. |
| metadata | {"openclaw":{"requires":{"env":"[Truncated]","bins":"[Truncated]","primaryModel":"any"},"permissions":["subprocess"]},"author":"Zuga-luga","license":"MIT","homepage":"https://github.com/Zuga-luga/ZugaShield","npm":"zugashield-openclaw-plugin"} |
7-layer AI security scanning plugin for OpenClaw. Protects all channels simultaneously by hooking into the Gateway — the single chokepoint for all traffic.
| Attack | Hook | Detection |
|---|---|---|
| Prompt injection | preRequest | 150+ signatures, unicode smuggling, encoding evasion |
| SSRF / Command injection | preToolExecution | Cloud metadata URLs, shell metacharacters (always fail-closed) |
| Secret / PII leakage | preResponse | API keys, tokens, credentials, high-entropy strings |
| Memory poisoning | preRecall | Embedded instructions, sleeper payloads in recalled memories |
| DNS exfiltration | preResponse | High-entropy subdomains, data-in-DNS patterns |
| Path traversal | preToolExecution | Directory traversal sequences, symlink attacks |
pip install "zugashield[mcp]"
npm install zugashield-openclaw-plugin
openclaw plugins install ./node_modules/zugashield-openclaw-plugin
openclaw restart
/shield status
Should show: CONNECTED with 7 active layers.
In openclaw.json under plugins.entries.openclaw-plugin.config:
fail_closed (default: true) — Block requests when scanner is downstrict_mode (default: false) — Block medium+ threats (not just high/critical)scan.inputs / scan.outputs / scan.tool_calls / scan.memory — Toggle individual hooksZugaShield spawns a Python MCP server as a managed child process. Each message, tool call, and response passes through the scanner in <15ms. The plugin uses OpenClaw's Gateway hooks, meaning one install protects Signal + Telegram + Discord + WhatsApp + web simultaneously.
Tool calls are always fail-closed regardless of configuration — SSRF and command injection are too dangerous to allow through even temporarily.