扫描报告
5 /100
lobster-coordinator
三层多Agent协调器（参考Claude Code架构），支持AgentTool单任务委托、Swarm团队协作、Coordinator模式全局调度。当任务复杂需要多Agent协作时自动激活。
Pure documentation skill describing a multi-agent coordination architecture with no executable code or suspicious behavior.
可以安装
This is a low-risk documentation-only skill. No action required.
| 资源类型 | 声明权限 | 推断权限 | 状态 | 证据 |
|---|---|---|---|---|
| 文件系统 | NONE | NONE | — | N/A - documentation only |
| 网络访问 | NONE | NONE | — | N/A - documentation only |
| 命令执行 | NONE | NONE | — | N/A - documentation only |
| 环境变量 | NONE | NONE | — | N/A - documentation only |
| 技能调用 | READ | READ | ✓ 一致 | SKILL.md describes platform-level orchestration |
| 剪贴板 | NONE | NONE | — | N/A - documentation only |
| 浏览器 | NONE | NONE | — | N/A - documentation only |
| 数据库 | NONE | NONE | — | N/A - documentation only |
目录结构
1 文件 · 6.2 KB · 212 行 Markdown 1f · 212L
└─
SKILL.md
Markdown
安全亮点
✓ Pure documentation skill with no executable code
✓ No suspicious patterns like base64 encoding, eval(), or obfuscation
✓ No credential harvesting or environment variable iteration
✓ No remote script execution patterns (curl|bash, wget|sh)
✓ Describes legitimate multi-agent coordination architecture
✓ No dependencies or third-party packages to audit
✓ No sensitive file paths accessed (~/.ssh, ~/.aws, .env)
✓ References Claude Code architecture - standard reference implementation