Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

敏感内容扫描器

v3.2.0

专业的敏感内容扫描器,支持 PII 检测(身份证/手机号/银行卡/邮箱/IP)、敏感词检测、置信度评分、多格式报告生成。适用于文档审查、安全审计、内容合规检查、隐私保护等场景。

1· 150·0 current·0 all-time
byqing@qinkai25

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for qinkai25/sensitive-content-scanner.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "敏感内容扫描器" (qinkai25/sensitive-content-scanner) from ClawHub.
Skill page: https://clawhub.ai/qinkai25/sensitive-content-scanner
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install sensitive-content-scanner

ClawHub CLI

Package manager switcher

npx clawhub@latest install sensitive-content-scanner
Security Scan
Capability signals
CryptoRequires walletRequires OAuth tokenRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name, description, SKILL.md and included files (pii_patterns.md, hashed sensitive words, scan_sensitive.py) are coherent: the code implements PII and keyword scanning, reporting, and supports CSV/JSON/encrypted dictionaries as described.
Instruction Scope
SKILL.md instructs users to attach documents and asserts scans run locally without uploading. The visible code implements local pattern checks, hashing and encrypted-dictionary loading, and report file generation (report.html). However the provided script is truncated in the package preview — there is no explicit network call shown in the excerpt, but the privacy claim cannot be fully verified without reviewing the entire script for any network I/O or telemetry. Also SKILL.md permits scanning filenames and file contents (expected) but gives broad instructions that could be misused to scan arbitrary files if an agent had file-system access.
!
Install Mechanism
No install spec or declared dependencies are provided, yet the script imports third-party modules (e.g., Crypto from pycryptodome, and likely libraries for docx/xlsx parsing). That mismatch is a practical and security concern: an operator may need to pip-install packages (network activity) or the script may fail in constrained environments. Lack of declared dependency/version information makes it harder to audit and increases the chance of unexpected behavior.
Credentials
The skill does not request environment variables, credentials, or config paths. The only notable thing is an internally derived deterministic password used to decrypt packaged encrypted dictionaries; this is self-contained and does not require external secrets.
Persistence & Privilege
Skill flags show no forced persistence (always:false) and there is no evidence it modifies other skills or system-wide settings. It generates a local report file (report.html), which is normal for this functionality.
What to consider before installing
This skill appears to implement what it claims (PII and keyword scanning with local report generation), but take these precautions before installing or running it: - Inspect the full scripts: review the remainder of scripts/scan_sensitive.py to confirm there are no network calls (requests, urllib, sockets) or unexpected subprocess calls that could exfiltrate data. The preview is truncated — full-file review is needed to verify the 'no upload' claim. - Run in a sandbox: until you confirm no network activity, run the scanner on non-sensitive test files inside an isolated environment (air-gapped VM or container). - Confirm dependencies: the script uses third-party Python packages (Crypto/pycryptodome, and likely python-docx/openpyxl etc.). Determine required packages and versions before installing; prefer installing from known package mirrors and pin versions. - Validate encrypted-dictionary behavior: the script derives a fixed password from embedded code to decrypt .enc dictionaries. Understand this mechanism and ensure encrypted dicts come from trusted sources; otherwise malicious dictionaries could be loaded. - Check report output and storage: reports are written to report.html in working directory — verify where it will be saved and ensure it doesn't expose sensitive content to other users or services. - If you need high assurance, ask the publisher for: dependency list, full source file(s), and an explicit statement that no telemetry or network I/O is performed; if publisher cannot provide these, treat the package as untrusted.

Like a lobster shell, security has layers — review code before you run it.

latestvk97ft3v8v489nt2r63w7078n9n85bpwq
150downloads
1stars
6versions
Updated 5d ago
v3.2.0
MIT-0

敏感内容扫描器

🎯 一句话说明

帮您检查文档中是否有敏感内容(身份证、手机号、密码等)或违禁词。

👤 适用人群

办公室文员、行政人员、文档审核人员 —— 无需技术背景


🚀 三种傻瓜式用法

方式一:快速扫描(内置规则)

操作

  1. 附件:您的文档文件(如 .docx.txt.pdf
  2. 说:"扫描"

示例

用户:帮我扫描这份文档 [附件:年度报告.docx]

会检测

  • 🔒 身份证号
  • 📱 手机号码
  • 💳 银行卡号
  • ✉️ 邮箱地址
  • 🌐 IP 地址
  • 🔑 密码/密钥等敏感词

方式二:自定义关键词扫描

操作

  1. 附件:您的文档文件
  2. 说:"扫描",然后告诉我要检查的关键词

示例

用户:扫描这份文档,检查这些词:密码、密钥、机密、内部 [附件:技术文档.docx]

支持的表达

  • "检查这些词:密码、密钥"
  • "扫描并检查:机密、绝密"
  • "用关键词 密码 密钥 机密 扫描"

方式三:使用数据字典文件扫描

操作

  1. 附件1:您的文档文件
  2. 附件2:数据字典文件(CSV 格式)
  3. 说:"用数据字典扫描"

数据字典格式(CSV):

关键词权重分类别
密码10技术敏感词
密钥10技术敏感词
机密8密级
内部5内部信息

示例

用户:用数据字典扫描这份文档 [附件1:项目文档.docx] [附件2:敏感词字典.csv]


📋 扫描结果说明

扫描完成后,会生成 HTML 格式报告(浏览器直接打开查看):

结果含义建议
✅ 安全(绿色)未发现敏感内容可以放心使用
⚠️ 低风险(浅绿)发现轻微问题可选处理或忽略
⚠️ 中风险(黄色)发现少量敏感内容建议人工复核
🚨 高风险(红色)发现严重敏感内容需要立即处理

报告特性

  • 📊 可视化仪表盘——统计卡片 + 风险指示条
  • 🎨 精美排版——响应式设计,手机也能看
  • 🔍 详情展开——每个文件的问题逐一列出
  • 🏷️ 置信度标注——高/中/低三色区分

也可通过 -f markdown 输出 Markdown 格式。


🎨 数据字典模板

如果您需要自定义数据字典,可以下载这个模板:

文件名敏感词字典模板.csv

内容格式

关键词,权重分,类别
密码,10,技术敏感词
密钥,10,技术敏感词
机密,8,密级
绝密,10,密级
内部,5,内部信息
公司名,5,商业信息

权重分说明

  • 10分:极高敏感度(如:密码、密钥)
  • 5-9分:高敏感度(如:机密、内部)
  • 1-4分:一般敏感度(如:内部资料)

📁 支持的文件格式

类型格式支持情况
Word 文档.docx✅ 完全支持
纯文本.txt✅ 完全支持
Markdown.md✅ 完全支持
Excel.xlsx✅ 完全支持
PDF.pdf⚠️ 文本型支持,扫描版不支持

❓ 常见问题

Q: 扫描需要多久? A: 一般文档几秒钟,大文档(100页以上)可能需要1-2分钟。

Q: 我的文档会被保存吗? A: 不会。扫描过程在本地完成,不会上传您的文档。

Q: 扫描结果保存在哪里? A: 默认生成 report.html,浏览器直接打开即可查看精美报告。

Q: 可以输出其他格式吗? A: 可以。-f html(默认,推荐)、-f markdown-f json

Q: 什么是权重分? A: 权重分表示敏感词的严重程度。分数越高,越需要关注。


💡 提示

  1. 定期扫描:重要文档发布前建议扫描
  2. 关键词定制:根据公司要求设置检查的敏感词
  3. 数据字典共享:可以创建公司统一的敏感词字典,大家一起用
  4. 结果保存:扫描报告建议保存,方便后续查阅
  5. 详细指南:查看 用户操作指南.md 获取更详细的使用说明

🔧 技术信息(可选了解)

扫描脚本scripts/scan_sensitive.py

命令行参考(如有需要):

# 快速扫描
python3 scan_sensitive.py 文档.docx

# 自定义关键词
python3 scan_sensitive.py 文档.docx -k "密码" -k "密钥"

# 使用数据字典
python3 scan_sensitive.py 文档.docx --dict-csv 敏感词字典.csv

版本:3.1.2 更新日期:2026-04-21

Comments

Loading comments...