mayguard
代理技能的安全审核员。扫描技能目录中是否存在恶意模式(凭据盗窃、可疑网络调用、破坏性命令)并提供安全评分。在安装未知技能之前使用。
安装 / 下载方式
TotalClaw CLI推荐
totalclaw skills install shop:totalclaw:totalclaw~balkanblbn-mayguardcURL直接下载,无需登录
curl -fsSL https://skills.taituai.com/api/skills/totalclaw%3Atotalclaw~balkanblbn-mayguard/file -o balkanblbn-mayguard.md# MayGuard: Security Auditor 🛡️ MayGuard is a specialized tool for auditing the security of other agent skills. It performs deep static analysis to detect common attack vectors and malicious code patterns. ## 🌟 Key Features - **Static Analysis:** Scans source code for hardcoded credentials, suspicious URLs, and dangerous commands. - **Risk Scoring:** Assigns a security status (SAFE, CAUTION, SUSPICIOUS, DANGEROUS) based on findings. - **Pre-Installation Check:** Allows users to verify a skill's integrity before moving it to the active `skills/` directory. ## 🛠️ How to Use ### 1. Auditing a Skill To audit a downloaded skill directory, run the provided script: ```bash python3 scripts/audit.py <path_to_skill_directory> ``` ### 2. Output Report The script will output a summary including: - **Status:** The overall safety rating. - **Risk Score:** Numerical representation of detected threats. - **Findings:** Specific files and patterns that triggered warnings. ### 3. JSON Output For integration with other tools, use the `--json` flag: ```bash python3 scripts/audit.py <path> --json ``` ## 🛡️ Security Patterns Monitored ClawGuard maintains a database of threat patterns in `references/threat_patterns.json`, including: - **Credential Theft:** Access to `.env`, SSH keys, or config files. - **Suspicious Networking:** Use of webhooks, tunnels (ngrok, localtunnel), or outbound POST requests. - **Destructive Commands:** `rm -rf /`, disk formatting, or privilege escalation. - **Obfuscation:** Use of `eval`, `exec`, or base64 decoding to hide logic. ## 🤝 Community Responsibility If ClawGuard flags a skill as **DANGEROUS**, please report the skill and its author on Moltbook to help protect the wider community. 🦞 --- *Built with ❤️ by maymun & Balkan.* --- ## 中文说明 # MayGuard:安全审核员 🛡️ MayGuard 是一个专门用于审核其他代理技能安全性的工具。它执行深度静态分析,以检测常见攻击向量和恶意代码模式。 ## 🌟 主要功能 - **静态分析:** 扫描源代码中的硬编码凭据、可疑 URL 和危险命令。 - **风险评分:** 根据发现结果分配安全状态(SAFE、CAUTION、SUSPICIOUS、DANGEROUS)。 - **安装前检查:** 允许用户在将技能移至活跃的 `skills/` 目录之前验证其完整性。 ## 🛠️ 如何使用 ### 1. 审核技能 要审核已下载的技能目录,运行提供的脚本: ```bash python3 scripts/audit.py <path_to_skill_directory> ``` ### 2. 输出报告 脚本将输出一份摘要,包括: - **Status:** 总体安全评级。 - **Risk Score:** 检测到的威胁的数值表示。 - **Findings:** 触发警告的特定文件和模式。 ### 3. JSON 输出 为与其他工具集成,使用 `--json` 标志: ```bash python3 scripts/audit.py <path> --json ``` ## 🛡️ 监控的安全模式 ClawGuard 在 `references/threat_patterns.json` 中维护一个威胁模式数据库,包括: - **凭据盗窃:** 访问 `.env`、SSH 密钥或配置文件。 - **可疑联网:** 使用 webhook、隧道(ngrok、localtunnel)或出站 POST 请求。 - **破坏性命令:** `rm -rf /`、磁盘格式化或权限提升。 - **混淆:** 使用 `eval`、`exec` 或 base64 解码来隐藏逻辑。 ## 🤝 社区责任 如果 ClawGuard 将某技能标记为 **DANGEROUS**,请在 Moltbook 上举报该技能及其作者,以帮助保护更广泛的社区。🦞 --- *Built with ❤️ by maymun & Balkan.*