可信 — 风险评分 5/100
上次扫描:17 小时前 重新扫描
5 /100
sub-agent-factory
Rapidly spawn and configure specialized sub-agents with templates for Research, Coding, and Analysis agents
A straightforward agent workspace factory that creates directories and generates per-agent SKILL.md files with no malicious behavior detected.
技能名称sub-agent-factory
分析耗时25.2s
引擎pi
可以安装
No action needed. The skill is a simple workspace generator with clear, scoped functionality.
资源类型声明权限推断权限状态证据
文件系统 NONE WRITE ✓ 一致 scripts/create_agent.sh:12 - mkdir -p creates agent subdirectories; scripts/crea…
命令执行 READ WRITE ✓ 一致 scripts/create_agent.sh:1 - shebang #!/usr/bin/env bash, script is invoked via s…
网络访问 NONE NONE No network calls found in any file
环境变量 NONE NONE No environment variable access found
凭据 NONE NONE No credential access or exfiltration
剪贴板 NONE NONE No clipboard access
浏览器 NONE NONE No browser interaction
数据库 NONE NONE No database access

目录结构

3 文件 · 1.3 KB · 51 行
Markdown 1f · 26L Shell 1f · 20L JSON 1f · 5L
├─ 📁 scripts
│ └─ 🔧 create_agent.sh Shell 20L · 402 B
├─ 📋 _meta.json JSON 5L · 136 B
└─ 📝 SKILL.md Markdown 26L · 835 B

安全亮点

✓ No external network requests or IP communications
✓ No credential harvesting or environment variable iteration
✓ No obfuscation techniques (base64, eval, etc.)
✓ No sensitive path access (~/.ssh, ~/.aws, .env)
✓ No remote script execution (curl|bash, wget|sh)
✓ No supply chain risk — no dependencies declared
✓ Script is idempotent (mkdir -p) and scoped to a single agents/ directory
✓ Output is controlled via parameterized heredoc with no injection risk (variables are used as metadata in a heredoc, not executed)