ClawHub
Back to skill

Security audit

沟通偏好工具箱(专业版)

Security checks for vulnerabilities and agentic risk

Overview

This is a preference-management skill whose file edits, command examples, sync, export, and optional credentials are disclosed and aligned with its stated purpose.

Install only if you want an agent to manage persistent communication preference files and optionally sync them to a Git or object-storage remote. Review the sync remote, exported files, and any cleanup or rollback command before running them, and keep tokens in a credential manager or environment variables rather than project files.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises rollback, export, sync, and command-execution capabilities without a prominent warning that it may modify local files and send data to remote repositories or object stores. In an agent setting, this can cause users to authorize actions affecting local state or data exfiltration without understanding the side effects, especially because the skill has Read/Write/Edit/Bash tools.

Credential Access

High
Category
Privilege Escalation
Content
| Git | 版本控制 | 可选（同步功能需要） | 系统自带或`apt install git` |
| Python 3.8+ | 运行时 | 可选（分析报告功能需要） | `apt install python3` |
### API Key 配置
- **Git仓库凭据**：通过SSH密钥或Personal Access Token，存储在系统凭据管理器
- **通知渠道凭据**：飞书/钉钉Webhook Token存储在环境变量
- **对象存储凭据**：AWS S3/阿里云OSS的AccessKey存储在环境变量
- **禁止**：在配置文件或脚本中硬编码任何凭据
Confidence
87% confidence
Finding
The skill explicitly incorporates credentialed operations involving SSH keys, Personal Access Tokens, webhooks, and cloud storage keys, while also exposing Bash and sync/export capabilities. In this context, encouraging agent-managed synchronization to external systems materially raises the risk of credential misuse, accidental disclosure in logs/configs, or exfiltration of synchronized preference data if execution boundaries are weak.

Static analysis

No suspicious patterns detected.