中文 EN

扫描报告

扫描新文件

⚠ 低风险 — 风险评分 15/100
上次扫描：2 天前 重新扫描
15 /100
Claude Code Enhancement
Multi-agent coordination framework for OpenClaw with memory, permission, workflow, and agent management capabilities
This is a legitimate multi-agent coordination framework with no malicious behavior. The skill implements Coordinator, Memory, Permission, Workflow, and Agent management without any suspicious file operations, network calls, credential harvesting, or hidden functionality.
技能名称Claude Code Enhancement
分析耗时39.6s
引擎pi
✓
可以安装
The skill is safe to use. Minor documentation gaps exist (e.g., BYPASS permission mode mentioned in docs but not fully implemented), but these do not constitute security risks.

安全发现 3 项

严重性 安全发现 位置
低危
Unnecessary subprocess import
coordinator.py imports subprocess module but never uses it. This creates a false impression of shell execution capability.
import subprocess
→ Remove unused import to avoid confusion
 coordinator/coordinator.py:9
低危
Documentation scope mismatch
SKILL.md mentions 'bypass' permission mode but permission.py only implements DEFAULT, AUTO, and PLAN modes. BYPASS mode is referenced in check() but never exposed as a settable option.
if self.mode == PermissionMode.BYPASS:
→ Either implement BYPASS mode fully or remove references from documentation
 permission/permission.py:60
提示
Memory directory auto-creation
MemorySystem automatically creates ~/.openclaw/workspace/memory/ on initialization. This is expected behavior for a memory persistence feature.
self.memory_dir.mkdir(parents=True, exist_ok=True)
→ No action needed - this is documented behavior
 memory/memory.py:26
资源类型声明权限推断权限状态证据
文件系统 NONE WRITE ✓ 一致 memory.py writes to ~/.openclaw/workspace/memory/ for user preferences
网络访问 NONE NONE — No network operations found
命令执行 NONE NONE — subprocess imported but never invoked
环境变量 NONE NONE — No os.environ access for credential harvesting
技能调用 NONE NONE — Internal module orchestration only
剪贴板 NONE NONE — No clipboard access
浏览器 NONE NONE — No browser automation
数据库 NONE NONE — No database operations
13 项发现
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/OpenClaw-增强组件-blue?style=for-the-badge&logo=rocket
README.md:4
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/Version-1.0.0-green?style=for-the-badge
README.md:5
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/Python-3.12+-yellow?style=for-the-badge
README.md:6
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/版本-1.0.0-green?style=for-the-badge
SKILL.md:5
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/许可证-MIT-orange?style=for-the-badge
SKILL.md:7
🔗
中危 外部 URL 外部 URL
https://streak-stats.demolab.com?user=ntaffffff&theme=dark&hide_border=true
SKILL.md:18
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/安全-企业级-red?style=for-the-badge
SKILL.md:74
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/记忆-永久保存-blue?style=for-the-badge
SKILL.md:110
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/进度-可视化-green?style=for-the-badge
SKILL.md:141
🔗
中危 外部 URL 外部 URL
https://contributors-img.web.app/image?repo=ntaffffff/openclaw-claude-code-enhancement
SKILL.md:287
🔗
中危 外部 URL 外部 URL
https://img.shields.io/badge/许可证-MIT-blue?style=for-the-badge
SKILL.md:307
🔗
中危 外部 URL 外部 URL
https://img.shields.io/github/stars/ntaffffff/openclaw-claude-code-enhancement?style=social
SKILL.md:320
🔗
中危 外部 URL 外部 URL
https://img.shields.io/github/forks/ntaffffff/openclaw-claude-code-enhancement?style=social
SKILL.md:323

目录结构

9 文件 · 75.4 KB · 2499 行
Python 7f · 1903L Markdown 2f · 596L
├─ ▾ 📁 agent
│ └─ 🐍 agent_tool.py Python 263L · 7.9 KB
├─ ▾ 📁 coordinator
│ └─ 🐍 coordinator.py Python 197L · 6.2 KB
├─ ▾ 📁 memory
│ └─ 🐍 memory.py Python 303L · 9.1 KB
├─ ▾ 📁 permission
│ └─ 🐍 permission.py Python 245L · 7.7 KB
├─ ▾ 📁 workflow
│ └─ 🐍 workflow.py Python 286L · 9.1 KB
├─ 🐍 main.py Python 215L · 6.9 KB
├─ 🐍 nlp_parser.py Python 394L · 12.2 KB
├─ 📝 README.md Markdown 266L · 6.6 KB
└─ 📝 SKILL.md Markdown 330L · 9.7 KB

依赖分析 4 项

包名版本来源已知漏洞备注
json builtin stdlib 否 Standard library only
uuid builtin stdlib 否 Standard library only
asyncio builtin stdlib 否 Standard library only
pathlib builtin stdlib 否 Standard library only

安全亮点

✓ No credential harvesting - no access to ~/.ssh, ~/.aws, .env, or similar sensitive paths
✓ No network exfiltration - no external IP connections or data transmission
✓ No shell execution - subprocess imported but never called
✓ No base64/eval obfuscation - all code is readable plaintext
✓ No hidden instructions in HTML comments or elsewhere
✓ No curl|bash or wget|sh remote script execution
✓ No data theft patterns (iterating os.environ for keys)
✓ Filesystem writes are limited to user preference storage (~/.openclaw/workspace/memory/)
✓ No suspicious GitHub URLs pointing to credential harvesting repos