Skill flagged — suspicious patterns detected

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

fliggy-trip-planner

v1.0.1

智能行程规划师,整合航班、酒店、景点数据,一键生成完整旅行方案。当用户需要规划旅行行程、制定旅游计划、安排度假方案或询问"去哪里玩""怎么安排行程"时使用此 skill。

1· 150·0 current·0 all-time
by厉云涵@yunhanli7

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for yunhanli7/fliggy-trip-planner.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "fliggy-trip-planner" (yunhanli7/fliggy-trip-planner) from ClawHub.
Skill page: https://clawhub.ai/yunhanli7/fliggy-trip-planner
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 fliggy-trip-planner

ClawHub CLI

Package manager switcher

npx clawhub@latest install fliggy-trip-planner
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description say it will aggregate flights, hotels, POIs and generate itineraries using flyai; the SKILL.md purely uses flyai CLI commands (search-flight, search-hotel, search-poi) consistent with that purpose.
!
Instruction Scope
The instructions explicitly tell the agent to detect and, if missing, install a global npm package (@fly-ai/flyai-cli) and then run CLI commands. That grants the skill broad runtime actions (network download, global install, execution of an arbitrary CLI) beyond simple local computation. The SKILL.md also instructs the agent to 'wait for installation' and to always rely on flyai real-time data, which increases dependence on that external binary. There are no instructions limiting or verifying the install (no checksum, no official homepage), and no guidance about sandboxing or user confirmation.
!
Install Mechanism
The repository contains no formal install spec, but the runtime instructions call for 'npm i -g @fly-ai/flyai-cli' if the binary is absent. Global npm installs pull code from the public registry and can run arbitrary postinstall scripts — a non-trivial supply-chain risk. The skill metadata does not provide a trusted source, homepage, or integrity checks for this package.
Credentials
The skill declares no environment variables or credentials — that aligns with its metadata. However, the external CLI it installs may itself request credentials or access tokens at runtime (not declared in the skill). Because the skill delegates data access to that third-party CLI, hidden credential prompts or config changes are possible even though the skill doesn't declare them.
Persistence & Privilege
always is false and the skill is user-invocable only. The skill does ask to install a global binary (which persists on the host), but there is no metadata requesting permanent platform privileges or modifications to other skills' configs.
What to consider before installing
This skill appears to do what it says (use flyai to build itineraries), but it requires installing and running an external npm CLI from an unknown source at runtime. That CLI will be downloaded and installed globally and can execute arbitrary code or request credentials. Before installing or running this skill: (1) ask the publisher for the official flyai package homepage, npm package link, and a checksum or signed release; (2) inspect the @fly-ai/flyai-cli package contents (or run it) in a sandbox/container first rather than allowing a global install on your machine; (3) prefer an installation with explicit provenance (GitHub releases, vendor site) and integrity checks; (4) be prepared that the CLI may request API tokens or store config locally — do not provide unrelated credentials; (5) if you cannot verify the flyai package, treat this skill as high-risk and avoid installing it on sensitive systems.

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

latestvk9751n9g50fvsjsmcare8y0wx1840g87
150downloads
1stars
2versions
Updated 3w ago
v1.0.1
MIT-0

智能行程规划师 (fliggy Trip Planner)

一站式旅行规划解决方案,基于 flyai 实时数据,自动生成包含航班、酒店、景点的完整行程。

触发场景

  • 用户说"帮我规划去XX的旅行"
  • 用户询问"XX天可以去哪里玩"
  • 用户需要安排度假/旅游行程
  • 用户询问旅行攻略或行程建议

执行前检查

重要:在开始任何行程规划之前,必须先检查并安装 flyai 依赖:

# Step 0: 检查并安装 flyai
which flyai >/dev/null 2>&1 || npm i -g @fly-ai/flyai-cli

如果检测到 flyai 未安装,立即执行安装命令,等待安装完成后再继续后续操作。

核心能力

1. 智能参数提取

从用户输入中提取:

  • 目的地:城市名称(必需)
  • 出发地:默认询问或推断
  • 天数:行程天数(默认3天)
  • 预算:经济型/舒适型/豪华型
  • 偏好:美食/文化/自然/购物/亲子
  • 日期:具体日期或"下周末"/"五一"等

2. 数据获取流程

Step 1: 搜索航班
  flyai search-flight --origin <出发地> --destination <目的地> --dep-date <日期> --back-date <返程日期> --sort-type 3

Step 2: 搜索酒店
  flyai search-hotel --dest-name <目的地> --poi-name <核心景点> --check-in-date <入住> --check-out-date <退房> --sort rate_desc --max-price <预算上限>

Step 3: 搜索景点
  flyai search-poi --city-name <目的地> --poi-level 5
  flyai keyword-search --query "<目的地> 美食/特色体验"

3. 行程生成逻辑

根据天数自动分配:

  • Day 1:抵达 → 酒店入住 → 市区核心景点 → 特色晚餐
  • Day 2:全天深度游(5A景区/主题路线)→ 夜景/演出
  • Day 3:周边景点/特色体验 → 返程

根据偏好调整:

  • 美食偏好:增加餐厅推荐,安排美食街
  • 文化偏好:增加博物馆、古迹、文化演出
  • 自然偏好:增加公园、山水景区、户外活动
  • 亲子偏好:增加游乐园、科技馆、互动体验

输出格式

必须包含以下模块:

1. 行程概览

  • 目的地、天数、总预算
  • 最佳出行日期
  • 行程亮点一句话总结

2. 交通方案

  • 往返航班对比表格
  • 推荐航班及理由
  • 预订链接

3. 住宿推荐

  • 2-3家酒店对比(位置、价格、特色)
  • 推荐酒店及理由
  • 酒店图片 + 预订链接

4. 每日行程

每天包含:

  • 时间线(上午/下午/晚上)
  • 景点/活动安排
  • 餐厅推荐
  • 交通提示
  • 景点图片 + 预订链接

5. 实用贴士

  • 天气提醒
  • 穿衣建议
  • 必带物品
  • 注意事项

6. 费用预算表

项目费用备注
往返机票¥XXX经济舱
酒店¥XXXX晚
景点门票¥XXX主要景点
餐饮交通¥XXX预估
总计¥XXX人均

图片与链接规范

  • 酒店图片![]({mainPic})
  • 景点图片![]({picUrl})
  • 航班预订[点击预订机票]({jumpUrl})
  • 酒店预订[点击预订酒店]({detailUrl})
  • 景点预订[点击预订门票]({jumpUrl})

示例对话

用户:帮我规划一个去成都的四天三晚行程,从北京出发,喜欢吃美食。

执行流程

  1. 提取参数:出发地=北京,目的地=成都,天数=4,偏好=美食
  2. 调用 flyai 搜索航班、酒店、景点
  3. 生成包含火锅、串串、川菜餐厅的行程
  4. 安排宽窄巷子、锦里、大熊猫基地等景点

注意事项

  1. 始终基于 flyai 实时数据,不要编造价格或航班信息
  2. 酒店推荐优先选择靠近核心景点或地铁便利的位置
  3. 行程节奏要合理,避免一天安排过多景点
  4. 预算估算要留有余地,标注"不含购物"
  5. 图片必须显示在预订链接之前

Comments

Loading comments...