← 返回 Skills 市场
79
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install shi-gou-guardian
功能描述
尸狗·警觉魄v2.0 - 高级安全防御与威胁情报，让AI像修士一样构建铁桶防线
安全使用建议
Before enabling this skill, ask the author for concrete implementation details: (1) exactly which commands, files, and system paths the skill will read or modify (e.g., /var/log, /proc, firewall rules); (2) which external services it will call and whether API keys are required; (3) whether the skill will ever perform destructive actions (kill processes, block IPs, isolate hosts) automatically, and if so what explicit confirmations or safety checks are enforced; (4) what the listed dependency skills do and what credentials they require. Do not provide any credentials or broad agent host permissions until you have those answers. If you must test it, run it in an isolated sandbox with no access to production systems or secrets and require explicit user confirmation for any blocking/remediation actions.
功能分析
Type: OpenClaw Skill
Name: shi-gou-guardian
Version: 2.0.0
The skill bundle defines a 'Security Guardian' persona for an AI agent, focusing on defensive security tasks such as threat detection, security auditing, and incident response. The SKILL.md file provides structured instructions for monitoring system processes, network connections, and file access, while adhering to security principles like Zero Trust and Least Privilege. No malicious code, data exfiltration logic, or harmful prompt injections were found; the content is entirely consistent with its stated purpose of providing a security defense framework.
能力评估
Purpose & Capability
The skill claims process/network/file monitoring, automated blocking/isolation, and integration with external threat‑intel services (MISP, AlienVault, VirusTotal). However, the metadata declares no required binaries, no config paths, and no environment variables or credentials. Realizing those capabilities would normally require host access (e.g., reading /proc, log files, packet capture), system tools (ps, netstat, tcpdump), or API keys for third‑party TI services — none are declared. This is an incoherence between claimed purpose and the declared requirements.
Instruction Scope
SKILL.md is high‑level and prescriptive (e.g., '识别 → 隔离 → 阻断 → 告警 → 记录', '启动威胁监控模式') but contains no concrete, constrained runtime steps, no explicit safe‑guards, and no indication it will request user confirmation before destructive operations. Because it's vague, an agent following these instructions could attempt broad actions (reading system state, invoking external APIs, killing processes, changing network/firewall rules) without clear limits.
Install Mechanism
This is an instruction‑only skill with no install spec and no code files, so nothing is written to disk or downloaded during installation. That lowers supply‑chain risk. Note: the lack of an install does not remove operational risk — the instructions still ask the agent to perform privileged actions if the agent has those capabilities.
Credentials
The doc references external threat‑intel sources (MISP, AlienVault, VirusTotal) and operations that typically need credentials or elevated host permissions, yet requires.env and primary credential fields are empty. This mismatch could lead the agent to prompt for credentials, attempt to use credentials from other contexts, or try to access system resources without explicit declaration. Dependencies on other skills are noted but their required credentials are not declared either.
Persistence & Privilege
always is false and the skill is user‑invocable (normal). However, the described automated response actions (blocking, isolation, cleanup) are high‑privilege operations if executed. If you allow the agent autonomous execution with system/network privileges, these instructions could cause disruptive changes. The skill itself does not request persistent presence or special platform privileges, but its semantics imply potentially destructive actions that should be gated.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install shi-gou-guardian - 安装完成后，直接呼叫该 Skill 的名称或使用
/shi-gou-guardian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
版本历史
v2.0.0
Security Guardian v2.0.0 introduces major new features and enhancements:
- Added threat intelligence integration (IOC/IOA) for improved detection accuracy.
- Introduced real-time monitoring: process, network, file, and resource activity.
- Implemented automated incident response playbooks for faster mitigation.
- Expanded compliance checks (e.g., 等保2.0, GDPR) and provided vulnerability/attack surface assessment.
- New baseline configuration checks and defense hardening suggestions.
- Enhanced reporting with structured, multi-dimensional security reports.
元数据
常见问题
尸狗·警觉魄v2.0 是什么？
尸狗·警觉魄v2.0 - 高级安全防御与威胁情报，让AI像修士一样构建铁桶防线. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 79 次。
如何安装 尸狗·警觉魄v2.0？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install shi-gou-guardian」即可一键安装，无需额外配置。
尸狗·警觉魄v2.0 是免费的吗？
是的，尸狗·警觉魄v2.0 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
尸狗·警觉魄v2.0 支持哪些平台？
尸狗·警觉魄v2.0 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 尸狗·警觉魄v2.0？
由 无为上人（@lt8899789）开发并维护，当前版本 v2.0.0。
推荐 Skills