Skill flagged — suspicious patterns detected

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

Tour Compare

v1.0.0

专业旅游线路对比分析,支持多平台商品链接和截图,提供价格、行程、评分等多维度智能对比与个性化推荐。

0· 89·0 current·0 all-time
byLiang@liangnex

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for liangnex/tour-compare.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Tour Compare" (liangnex/tour-compare) from ClawHub.
Skill page: https://clawhub.ai/liangnex/tour-compare
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 tour-compare

ClawHub CLI

Package manager switcher

npx clawhub@latest install tour-compare
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description (旅游线路对比) matches the included code: crawler (ota-crawler.js), OCR (image-recognizer.js), analyzer and exporter. The declared capabilities (URL fetch, screenshot OCR, JSON input, PNG export) align with the code files and package.json optional deps (puppeteer, tesseract.js, canvas). No unrelated credentials or bizarre binaries are requested.
!
Instruction Scope
SKILL.md and docs instruct the agent to fetch arbitrary OTA product URLs, OCR user-provided screenshots, write HTML/PNG reports to file:///Users/zihui/.openclaw/workspace/..., and run local CLI scripts. The packaged scripts (compare.sh, demo.sh) will run node src/index.js and demo.sh uses read -p /dev/tty which can block automated runs. The SKILL.md also contains unicode control chars (prompt-injection signal). Overall the instructions go beyond purely stateless text processing (they instruct network fetches, filesystem writes, and local installs) — reasonable for this tool but should be executed with care and explicit consent.
!
Install Mechanism
There is no declared install spec in the registry metadata, but package.json and scripts expect npm installs. compare.sh will auto-run npm install if node_modules is missing, which causes dependencies (optional deps include puppeteer and canvas) to be fetched at runtime. Puppeteer will fetch Chromium (large binary) and canvas may require system libraries. package-lock references a non-standard registry mirror (registry.anpm.alibaba-inc.com) in some entries, increasing supply-chain observation risk. No direct arbitrary remote archive downloads were found, but implicit npm installs and Chromium downloads are a non-trivial runtime action.
Credentials
The skill requests no environment variables, no credentials, and no config paths in the registry metadata. The code and docs do not require API keys or other secrets. That is proportionate for a web-scraping/OCR/comparison tool. (Caveat: running npx clawhub publish examples or npx clawhub login noted in docs would require user tokens — these are optional publishing steps, not core to the skill's function.)
Persistence & Privilege
The skill is not 'always: true' and does not request elevated privileges. However it will write local report files (examples show a user-local file:// path) and the packaged demo/CLI will run npm install and write to the workspace. Autonomous invocation is allowed (default), which combined with the earlier concerns (auto-installs and prompt-injection markers) increases blast radius — consider requiring explicit user approval before running network installs or the crawler.
Scan Findings in Context
[unicode-control-chars] unexpected: SKILL.md contains unicode control characters flagged by the scanner. These can be used to hide or alter visible text (prompt-injection technique). This is not necessary for a travel comparison document and is suspicious — it could be accidental formatting or an attempt to obscure embedded instructions. Inspect SKILL.md raw bytes before trusting automated execution.
What to consider before installing
What to consider before installing or running this skill: - The code and docs match the described purpose (URL scraping, OCR, analysis), but the package will try to install node dependencies at runtime (compare.sh auto-runs npm install). Puppeteer (optional) will download Chromium; canvas/tesseract.js have native or large-assets requirements. If you run this on your machine, expect big downloads and possible native build steps. - SKILL.md contains unicode control characters (a prompt-injection signal). Treat this as suspicious: view the raw SKILL.md (hex/visible control-char safe viewer) and confirm there are no hidden instructions or data before running automated processes. - package-lock entries reference a non-standard registry mirror (registry.anpm.alibaba-inc.com). Prefer installing only from official registries or inspect package-lock and network traffic. Consider running npm install with a lockfile you trust or in a sandbox. - Do not run the demo script or compare.sh in an environment with sensitive data or unattended automation. demo.sh uses read -p and /dev/tty (interactive) which can hang or behave unexpectedly in non-interactive agents. compare.sh will install deps automatically — to avoid unexpected installs, run npm install manually after reviewing package.json and package-lock. - Run in an isolated sandbox (VM/container) or code-audit first: search for network endpoints, hard-coded URLs, exfiltration logic, or unexpected child_process.exec usage. Pay attention to any code that posts data to remote endpoints or runs arbitrary shell commands. - If you only need the comparison logic without crawling, use JSON-mode inputs (no network fetch) and avoid enabling puppeteer/optional deps. Consider disabling autonomous execution of the skill in your agent unless you reviewed/approved its behavior. - If you want to proceed, recommended steps: inspect SKILL.md raw, review src/crawler/ota-crawler.js and src/crawler/image-recognizer.js for any outbound endpoints, run npm install with a trusted registry and verify packages, and execute in a sandboxed environment.

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

latestvk976ptmmek730155an3vkwyse58413pp
89downloads
0stars
1versions
Updated 3w ago
v1.0.0
MIT-0

🦐 tour-compare - 线路对比分析师

专业的旅游商品对比助手,帮你快速做出明智决策


📋 技能概述

中文名: 线路对比分析师
英文名: tour-compare
版本: v0.3.0
作者: 小虾

核心价值:

  • 📊 智能对比 - 多个旅游商品横向对比,一眼看出差异
  • 🎯 决策辅助 - 基于人群特征和偏好,给出个性化推荐
  • ⚠️ 避坑提醒 - 识别低价团、购物团、隐形消费
  • 💡 实质分析 - 不只是信息罗列,提供有洞察的对比总结

🎯 触发条件

使用以下关键词时触发此技能:

直接触发

  • "对比" + "旅游"/"跟团游"/"线路"/"行程"
  • "哪个更好" + 旅游商品
  • "推荐" + "去 XX 玩"/"旅游线路"
  • "帮我选" + 旅游产品
  • "/tour-compare" 命令

自然语言触发

  • "这两个云南游哪个值得买?"
  • "飞猪上有两个团,帮我看看"
  • "想去大理丽江,有什么推荐?"
  • "带父母去旅游,选哪个团好?"

输入方式触发

  • 发送 2 个及以上商品链接(携程/飞猪/同程等)
  • 发送 商品截图(自动 OCR 识别)
  • 发送 商品信息(JSON 格式)

📥 输入方式

1️⃣ URL 链接(推荐⭐⭐⭐⭐⭐)

支持的 OTA 平台(8 大主流):

平台域名示例状态
✈️ 携程ctrip.comm.ctrip.com
🐷 飞猪fliggy.coma.feizhu.com
🐫 同程ly.comm.ly.com
🐝 马蜂窝mafengwo.cnm.mafengwo.cn
🎒 穷游qyer.comm.qyer.com
🍱 美团旅行meituan.comtravel.meituan.com
🐮 途牛tuniu.comm.tuniu.com
🐘 驴妈妈lvmama.comm.lvmama.com

使用示例:

用户:对比这两个
https://a.feizhu.com/0HeTSg
https://a.feizhu.com/3PT4IS

2️⃣ 截图 OCR(方便⭐⭐⭐⭐)

支持格式: PNG / JPG / JPEG / WEBP

识别内容:

  • 价格、评分、评价数
  • 行程天数、酒店星级
  • 购物店数量、特色标签

使用示例:

用户:[发送两张商品截图]

助手:🔍 正在识别截图...
✅ 截图 1 识别成功:云南大理丽江 4 天 3 晚...
✅ 截图 2 识别成功:丽江大理香格里拉 5 天 4 晚...
📊 开始对比...

3️⃣ JSON 格式(测试⭐⭐⭐)

最小格式:

{
  "platform": "飞猪",
  "title": "云南 6 日游",
  "price": 3299,
  "rating": 4.8
}

完整格式:

{
  "platform": "飞猪",
  "title": "云南大理丽江 4 天 3 晚纯玩小团",
  "price": 558.8,
  "rating": 4.9,
  "reviewCount": 230,
  "shoppingStops": 0,
  "hotelStars": 3,
  "days": 4,
  "groupSize": 15,
  "features": ["玉龙雪山", "洱海", "纯玩无购物"],
  "goodRate": "96%"
}

📤 输出结构

每次对比分析,系统会输出三部分

1️⃣ 文字版对比总结(核心)

📊 旅游商品对比分析
==================================================

✅ 推荐"6 人小团 5 天 4 晚" - 评分完美、小团体验更好

📋 核心差异

维度          商品 1          商品 2       
────────────  ─────────────  ─────────────
💰 价格       ¥558.8         ¥680         
⭐ 评分       4.9 分          5.0 分        
📅 天数       4 天 3 晚        5 天 4 晚      
👥 团型       15 人小团        6 人小团      
🏨 酒店       3 钻            4 钻         

🎯 关键决策因素

1. 团型差异:15 人团 vs 6 人团
   💡 6 人小团人更少,导游照顾更周到

2. 价格差距:相差¥121.2 (22%)
   💡 平均每天多¥24,换来更好体验

💰 性价比分析

✅ 商品 1: 性价比明显更高 (指数:156)

📍 怎么选

• 追求性价比:商品 1
  理由:价格便宜 22%
• 追求品质:商品 2
  理由:评分完美,小团体验好

2️⃣ 可视化报告链接(HTML)

📄 可视化报告
==================================================

🔗 file:///Users/zihui/.openclaw/workspace/tour-compare-packages.html
同目的地套餐对比

💡 提示:点击链接在浏览器中打开完整报告

报告内容:

  • 决策树流程图
  • 详细对比表格
  • 用户评价对比(好评/差评标签云)
  • 费用明细对比
  • 风险提示
  • 最终建议

3️⃣ 相关问题追问(引导)

💬 相关问题
==================================================

1. 想知道价格差异主要体现在哪些方面吗?
2. 需要我详细对比每日行程安排吗?
3. 想了解具体酒店信息和位置吗?
4. 需要对比退改政策和风险提示吗?

有任何问题随时问我!🦐

🎯 核心功能

功能 1: 智能对比分析

对比维度:

  • 💰 价格(团费 + 自费 + 餐饮 + 购物)
  • ⭐ 评分(用户评价 + 好评率)
  • 📅 行程(天数 + 路线 + 景点)
  • 👥 团型(人数 + 用车 + 导游)
  • 🏨 酒店(星级 + 位置 + 设施)
  • 🛍️ 购物(购物店数量 + 自费项目)
  • 🔄 退改(取消政策 + 改期规则)

分析深度:

  • 优缺点对比
  • 性价比指数计算
  • 关键决策因素提取
  • 场景化推荐

功能 2: 人群画像适配

支持人群:

人群权重偏好推荐逻辑
👴 老人少购物、轻松行程、医疗便利推荐纯玩团、行程舒缓
👨‍👩‍👧‍👦 亲子亲子设施、安全、趣味性推荐亲子友好、安全系数高
💑 蜜月私密性、高星酒店、浪漫体验推荐独立团、高档酒店
🎓 学生性价比、自由度、社交属性推荐经济团、自由行时间多
👫 朋友自由度、体验、拍照推荐小团、拍照点多的路线
💼 商务品质、效率、服务推荐高端团、专车服务

功能 3: 避坑提醒

识别规则:

风险类型识别关键词警示级别
🔴 低价团价格<¥2000 且天数≥5
🔴 购物团购物店≥3 个
🟡 非官方星级"准 X 钻"
🟡 车览/远观"车览"、"远观"
🟡 自理项目"费用自理"
🟢 行程紧张每天景点>4 个
🟢 评价数少评价<20 条

功能 4: 跨目的地对比

对比场景:

  • 日本 vs 云南(出国 vs 国内)
  • 三亚 vs 大理(海岛 vs 古城)
  • 泰国 vs 新加坡(东南亚对比)

额外维度:

  • 🛂 签证要求
  • 💱 货币/汇率
  • 🗣️ 语言障碍
  • ✈️ 飞行时间
  • 🌤️ 最佳季节

🚀 使用示例

示例 1: URL 链接对比

用户:
对比这两个云南游
https://a.feizhu.com/0HeTSg
https://a.feizhu.com/3PT4IS

助手:
📊 旅游商品对比分析
==================================================

✅ 推荐"6 人小团 5 天 4 晚" - 评分完美、小团体验更好

[完整对比报告...]

📄 可视化报告
🔗 file:///Users/zihui/.openclaw/workspace/tour-compare-feizhu-compare.html

💬 相关问题
1. 想知道价格差异主要体现在哪些方面吗?
2. 需要我详细对比每日行程安排吗?
3. 想了解具体酒店信息和位置吗?

示例 2: 截图对比

用户:[发送两张商品截图]

助手:
🔍 正在识别截图...

✅ 截图 1 识别成功:
   云南大理丽江 4 天 3 晚纯玩小团
   价格:¥558.8
   评分:4.9 分
   酒店:3 钻

✅ 截图 2 识别成功:
   丽江大理香格里拉 5 天 4 晚 6 人小团
   价格:¥680
   评分:5.0 分
   酒店:4 钻

📊 开始对比...
[完整对比报告...]

示例 3: 智能推荐

用户:
我想带父母去云南玩,预算 5000,有什么推荐?

助手:
🎯 智能推荐报告
==================================================

搜索条件:云南 | 预算¥5000 | 老人 | 6 天

为什么推荐这个目的地

✅ 气候宜人,四季如春
✅ 医疗配套完善,昆明/丽江有三甲医院
✅ 行程节奏可调节,适合老人

🏆 推荐商品 Top3

🥇 云南 6 天 5 晚品质团
   平台:携程 | 价格:¥3600 | 评分:4.8
   亮点:纯玩无购物 | 接送机 | 4 钻酒店

[更多推荐...]

示例 4: 跨目的地对比

用户:
日本和云南,去哪里玩比较好?

助手:
🌏 目的地决策分析
==================================================

这是两个完全不同的旅行体验

📋 核心差异

| 维度 | 日本 | 云南 |
|─────|─────────|─────────|
| 💰 价格 | ¥8,000+ | ¥1,500+ |
| 📅 天数 | 6-7 天 | 4 天 |
| 🛂 签证 | 需要 | 无需 |
| 🎯 体验 | 城市购物 | 自然风光 |

💡 怎么选

选 日本 如果:
• 预算充足、喜欢购物美食、想体验异国文化

选 云南 如果:
• 预算有限、喜欢自然风光、带老人小孩

📄 可视化报告
🔗 file:///Users/zihui/.openclaw/workspace/tour-compare-destinations.html

📁 项目结构

skills/tour-compare/
├── SKILL.md                  # 技能文档(本文件)
├── README.md                 # 使用说明
├── FEATURES.md               # 功能总结
├── QUICKSTART.md             # 快速入门
├── CHANGELOG.md              # 更新日志
├── package.json              # 依赖配置
├── scripts/
│   ├── compare.sh            # CLI 入口
│   └── demo.sh               # 演示脚本
├── src/
│   ├── index.js              # 主入口
│   ├── crawler/
│   │   ├── ota-crawler.js    # URL 抓取
│   │   └── image-recognizer.js # 截图 OCR
│   ├── analyzer/
│   │   ├── comparator.js     # 对比引擎
│   │   ├── recommender.js    # 推荐引擎
│   │   └── analyzer.js       # 分析引擎
│   ├── ui/
│   │   ├── renderer.js       # 文字输出
│   │   └── summary-template.js # 输出模板
│   └── config/
│       └── personas.js       # 人群画像
├── docs/
│   ├── INPUT_GUIDE.md        # 输入方式指南
│   ├── OUTPUT_FLOW.md        # 输出流程
│   └── PLATFORMS.md          # 支持平台
└── examples/
    └── usage.md              # 使用示例

📦 依赖安装

基础版(JSON 输入)

cd skills/tour-compare
npm install

完整版(所有功能)

npm install puppeteer cheerio canvas tesseract.js

依赖说明:

  • puppeteer - URL 抓取(可选)
  • cheerio - HTML 解析(可选)
  • canvas - 图片导出(可选)
  • tesseract.js - 截图 OCR(可选)

🔧 命令

# 对比商品
./scripts/compare.sh compare <商品 1> <商品 2> [...]

# 智能推荐
./scripts/compare.sh recommend --destination <目的地> --budget <预算> --group <人群>

# 深度分析
./scripts/compare.sh analyze <商品> --deep

# 截图识别
./scripts/compare.sh recognize <截图路径>

# 截图对比
./scripts/compare.sh compare-images <截图 1> <截图 2>

🎯 使用场景

场景 1: 用户在两个商品间纠结

用户:这两个云南游哪个更好?
[发送两个链接]

助手:[对比分析 + 推荐 + 报告链接]

场景 2: 用户有需求但不确定选什么

用户:想带父母去旅游,有什么推荐?

助手:[询问目的地/预算/时间 → 推荐商品]

场景 3: 用户分享截图

用户:[发送截图]
这个团怎么样?

助手:[OCR 识别 → 分析 → 避坑提醒]

场景 4: 跨目的地决策

用户:日本和云南,去哪里好?

助手:[跨目的地对比 + 决策建议]

⚠️ 注意事项

数据准确性

  • 抓取的数据可能有延迟
  • 价格实时波动,以官网为准
  • 建议出行前再次确认

合规性

  • 遵守 OTA 平台 robots.txt
  • 控制抓取频率
  • 不存储用户个人信息

免责声明

  • 推荐仅供参考
  • 最终决策由用户自行判断
  • 不承担因选择产生的责任

📈 后续迭代

短期 (v0.4.0)

  • 添加重试机制和错误处理优化
  • 支持更多 OTA 平台(马蜂窝、穷游完整支持)
  • 优化 OCR 识别率
  • 添加单元测试

中期 (v0.5.0)

  • 历史价格追踪
  • 行程地图可视化
  • 用户评价情感分析
  • Web 界面原型

长期 (v1.0.0)

  • 完整 Web 应用
  • REST API 服务
  • 浏览器插件
  • 多语言支持

📝 版本历史

v0.3.0 (2026-04-01)

  • ✅ 截图 OCR 识别功能
  • ✅ URL 链接抓取完善(支持 8 大平台)
  • ✅ 标准化输出流程
  • ✅ 可视化报告生成

v0.2.0 (2026-04-01)

  • ✅ URL 链接抓取
  • ✅ 图片导出功能
  • ✅ CLI 改进

v0.1.0 (2026-03-31)

  • ✅ 初始版本
  • ✅ JSON 输入对比
  • ✅ 智能推荐
  • ✅ 深度分析

🎬 快速开始

最简单的使用方式:

  1. 在对话中直接发送商品链接或截图
  2. 系统自动识别并对比
  3. 查看对比报告

无需记忆任何命令!


Made with 🦐 by 小虾

最后更新:2026-04-01

Comments

Loading comments...