/install axiomata-guard-scanner
Axiomata Guard Scanner
Universal OpenClaw skill security scanner Impersonal — works for any agent
Description
Axiomata Guard Scanner protects OpenClaw agents by scanning skills for security threats. It uses multiple "vaccines" (detection engines) to identify malicious patterns before installation.
Trigger: Before installing any skill, especially from ClawHub.
Security Layers
Layer 1: ClawHub Malicious Pattern Check (VAX-001)
Checks for known malicious patterns:
- Malicious binary downloads (openclawcli.zip)
- RCE via glot.io snippets
- Malware via GitHub releases
- Password-protected archives
Layer 2: C2 & Data Exfiltration Detection (VAX-027)
Detects command & control infrastructure:
- Suspicious DNS lookups
- Discord/Telegram webhooks
- Bit.ly / short URL redirects
- Exfiltration patterns
Layer 3: Cross-Vector Attack Chain (VAX-028)
Correlates findings from other vaccines:
- Multiple attack vectors
- Chain escalation patterns
- Combined threat assessment
Layer 4: Rootkit & Bootkit Detection (VAX-029)
Detects kernel-level threats:
- System manipulation patterns
- Driver injection
- UEFI threats
Layer 5: Package Ecosystem Attacks (VAX-030)
Detects package-level attacks:
- typosquatting
- dependency confusion
- malicious packages
Usage
Scan a skill file
python3 scripts/guard_scanner.py --file \x3Cskill-path>
Scan skill code directly
python3 scripts/guard_scanner.py --code "\x3Cskill code>"
JSON output
python3 scripts/guard_scanner.py --file \x3Cskill-path> --json
Output Format
{
"scanner": "Axiomata Guard Scanner",
"version": "1.0.0",
"skill_name": "...",
"global_threat_level": "CLEAN | LOW | MEDIUM | HIGH | CRITICAL",
"global_score": 0-300,
"decision": "APPROVE | WARN | NEUTRALIZE | ISOLATE",
"triggered_vaccines": [...],
"summary": {...}
}
Threat Levels
| Level | Score | Action |
|---|---|---|
| CLEAN | 0 | APPROVE |
| LOW | 1-19 | APPROVE with monitoring |
| MEDIUM | 20-49 | WARN — manual review |
| HIGH | 50-79 | NEUTRALIZE |
| CRITICAL | 80+ | ISOLATE immediately |
In Altum Per Security. Axiomata Guard Scanner v1.0.0
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install axiomata-guard-scanner - 安装完成后,直接呼叫该 Skill 的名称或使用
/axiomata-guard-scanner触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Axiomata Guard Scanner 是什么?
Axiomata Guard Scanner — Universal security scanner for any OpenClaw skill. Use when: (1) scanning a skill for security threats before installation, (2) chec... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 107 次。
如何安装 Axiomata Guard Scanner?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install axiomata-guard-scanner」即可一键安装,无需额外配置。
Axiomata Guard Scanner 是免费的吗?
是的,Axiomata Guard Scanner 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Axiomata Guard Scanner 支持哪些平台?
Axiomata Guard Scanner 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Axiomata Guard Scanner?
由 Kofna3369(@kofna3369)开发并维护,当前版本 v1.0.1。