Skill flagged — suspicious patterns detected

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

tiktok-android-720p

v1.0.0

使用 ADB 自动化 TikTok 互动。支持 AI 智能评论(Claude/GPT-4/OpenRouter 视觉分析)、搜索话题、评论、点赞、收藏视频、发布内容。无需网页抓取,无 CAPTCHA,智能 UI 识别实现 100% 成功率。

0· 70·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for molin-g/tiktok-android-720p.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "tiktok-android-720p" (molin-g/tiktok-android-720p) from ClawHub.
Skill page: https://clawhub.ai/molin-g/tiktok-android-720p
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 tiktok-android-720p

ClawHub CLI

Package manager switcher

npx clawhub@latest install tiktok-android-720p
Security Scan
Capability signals
Crypto
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The code and SKILL.md match the stated purpose (ADB-driven TikTok automation, searching, commenting, liking, publishing). However the registry metadata claims 'required env vars: none' and 'required binaries: none' while the skill clearly requires adb on PATH and—if AI comment mode is used—API keys (ANTHROPIC_API_KEY / OPENAI_API_KEY / OPENROUTER_API_KEY). That metadata omission is an incoherence the publisher should have declared.
!
Instruction Scope
Runtime instructions and code include actions beyond simple UI clicks: deleting device media (rm -f /sdcard/DCIM/Camera/*.mp4), taking screenshots, encoding images and sending them to external AI APIs, downloading videos from URLs, and writing config/.env files. Deleting files on the connected Android device is destructive but justified by the 'publish' workflow; nonetheless it is a high-impact action and should be clearly disclosed and confirmed by the user. The setup wizard will prompt for and persist API keys to .env.
Install Mechanism
This is an instruction-and-code bundle with no remote install/download steps in the manifest (no external installers or archive downloads). All code runs locally. That lowers supply-chain install risk, but running arbitrary code from an untrusted source still requires caution.
!
Credentials
Requested environment access is broadly proportional to features (AI providers for AI comments, optional ANDROID_DEVICE_ID). But the registry declared no required env vars while the code expects ANTHROPIC_API_KEY / OPENAI_API_KEY / OPENROUTER_API_KEY when AI mode is selected. The setup wizard writes API keys into a local .env file (cleartext), which is a privacy/secret-management concern. No unrelated cloud credentials (AWS, etc.) are requested, which is good.
Persistence & Privilege
The skill is not configured 'always: true' and does not request system-wide privileges. It will create/overwrite files in the working directory (config.py, .env, .bot_settings.json) and performs destructive actions on the connected Android device (removes files from /sdcard/DCIM/Camera/). Those are expected for publish workflows but are high-impact and must be approved by the user.
What to consider before installing
This package implements an ADB-based TikTok bot that does what it says, but there are some red flags you should review before installing and running it: - Metadata mismatch: The registry claims no required env vars or binaries, but the skill needs adb on PATH and will ask for AI API keys if you enable AI comments. Treat the registry metadata as incomplete and rely on the README/SKILL.md and code. - Secrets handling: The interactive setup writes API keys into a local .env file in cleartext. If you supply API keys, consider using a secure secret store or removing keys after use. Inspect setup.py to see where it writes keys. - Destructive device actions: The publish workflow runs rm -f /sdcard/DCIM/Camera/*.mp4 on the connected Android device. Backup any important media on the device before running the tool and/or remove the publish/cleanup steps if you don't want deletion. - Hardcoded / absolute paths: Example scripts (run_complete_session.py, run_full_campaign.py) insert an absolute user path into sys.path (/Users/...), which looks like leftover test/configuration code. Review and remove/adjust those lines before running. - External network calls: If you enable AI mode, the skill will encode screenshots and send them to external AI endpoints (Anthropic/OpenAI/OpenRouter). This will leak screenshots/content to those services and may incur costs. Audit ai_comments.py to confirm providers and endpoints. - Running untrusted code: There is no remote install step, but these are executable Python scripts from an unknown source. If you decide to run it, do so in an isolated environment (non-production machine, container, VM) and inspect/modify the code (especially lines that delete files or call subprocess) to enforce safety. - Legal/ToS risk: Automated commenting/interaction on TikTok may violate platform terms of service and can lead to account action. Use conservative rates and avoid abusive/spammy behavior. If you want, I can: (1) point to the exact lines that delete device files and store API keys, (2) produce a minimal-safe patch that disables deletion and .env writes, or (3) list all places where network requests are made for your further review.

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

latestvk976wmzm57dmygb33qdw9v0f0n84vv9b
70downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

TikTok Android 机器人

使用 ADB 在 Android 设备上自动化 TikTok 互动。支持 AI 智能评论、搜索、评论、点赞、收藏、发布模式,配备智能 UI 识别和备用坐标。

功能说明

  • 搜索模式 - 搜索话题并评论相关视频
  • 探索模式 - 与推荐页视频互动
  • 互动模式 - 点赞、收藏、可选评论视频(支持概率控制)
  • 发布模式 - 从 URL 或本地文件上传发布视频
  • AI 智能评论 - 支持 Claude/GPT-4/OpenRouter 视觉分析视频内容
  • 智能 UI 识别 - 使用 uiautomator 动态检测图标位置
  • 备用坐标 - UI 检测失败时使用 720x1280 屏幕的固定坐标

前置要求

  • 已启用 USB 调试的 Android 设备(720x1280 分辨率)
  • 已安装 ADB (Android Debug Bridge)
  • 设备上已登录 TikTok 应用
  • Python 3.9+

快速开始

1. 自动设置(推荐)

首次运行会自动启动设置向导,引导您完成配置:

python3 tiktok_bot.py search --topics fitness --videos 5

设置向导会要求您:

  1. 选择感兴趣的话题
  2. 选择评论模式(静态模板 或 AI生成)
  3. 根据选择的模式配置相应参数

2. 设置 Android 设备

启用 USB 调试:

设置 → 关于手机 → 点击"构建号"7次
设置 → 开发者选项 → 启用"USB 调试"

通过 USB 连接并授权您的电脑。

3. 验证连接

adb devices
# 应显示:192.168.11.11:5555    device

adb shell wm size
# 应显示:Physical size: 720x1280

4. 安装依赖

pip install -r requirements.txt

5. AI 配置(可选)

如果您选择了 AI 评论模式,需要配置 API 密钥:

# Claude (Anthropic)
export ANTHROPIC_API_KEY="your-api-key"

# OpenAI (GPT-4)
export OPENAI_API_KEY="your-api-key"

# OpenRouter
export OPENROUTER_API_KEY="your-api-key"

或使用 .env 文件(由 setup.py 自动创建)。

使用方法

搜索模式

搜索话题并评论相关视频:

# 单话题,5 个视频
python3 tiktok_bot.py search --topics fitness --videos 5

# 多话题
python3 tiktok_bot.py search --topics "fitness,cooking,travel" --videos 3

# 指定设备 ID
python3 tiktok_bot.py search --topics gaming --videos 5 --device 192.168.11.11:5555

工作流程:

  1. 搜索每个话题
  2. 从搜索结果中打开视频
  3. 从模板发布评论
  4. 防止重复评论

探索模式

评论推荐页的随机视频:

python3 tiktok_bot.py explore --videos 10

工作流程:

  1. 从推荐页开始
  2. 发布通用评论
  3. 滑动到下一个视频

互动模式

点赞、可选收藏/评论(默认只点赞):

# 默认:仅点赞(100%概率)
python3 tiktok_bot.py interact --videos 10

# 点赞 + 收藏
python3 tiktok_bot.py interact --videos 10 --favorite

# 点赞 + 收藏 + 评论
python3 tiktok_bot.py interact --videos 5 --favorite --comment

# 随机概率:点赞50%,收藏30%
python3 tiktok_bot.py interact --videos 10 --favorite --like-rate 50 --favorite-rate 30

工作流程:

  1. 从推荐页(For You)开始
  2. 按概率点赞视频(智能 UI 识别 + 备用)
  3. 按概率收藏视频(智能 UI 识别 + 备用)
  4. 如启用则评论(使用通用模板)
  5. 滑动到下一个视频

说明: --topics 参数仅适用于 search_mode

概率说明:

  • --like-rate: 点赞概率 1-100,默认 100
  • --favorite-rate: 收藏概率 1-100,默认 100

防重复机制:

  • 自动跳过已点赞的视频
  • 自动跳过已收藏的视频
  • 基于会话内记录,关闭程序后重置

发布模式

上传并发布视频:

# 从 URL
python3 tiktok_bot.py publish --video "https://example.com/video.mp4" --description "我的视频 #fyp"

# 从本地文件
python3 tiktok_bot.py publish --video "/path/to/video.mp4" --description "看看这个!"

# 指定设备 ID
python3 tiktok_bot.py publish --video "https://example.com/video.mp4" --description "我的视频" --device 192.168.11.11:5555

工作流程:

  1. 清理相册(删除旧视频)
  2. 下载/上传视频到设备
  3. 运行媒体扫描
  4. 启动 TikTok 并等待加载
  5. 通过 TikTok 应用发布
  6. 发布后清理

设备设置

启用 USB 调试

设置 → 关于手机 → 点击"构建号"7次
设置 → 开发者选项 → 启用"USB 调试"

验证连接

adb devices
# 应显示:192.168.11.11:5555    device

adb shell wm size
# 应显示:Physical size: 720x1280

坐标配置 (720x1280)

搜索导航

元素XY
搜索图标660106
搜索输入框36064
搜索按钮68464

评论操作

元素XY
评论图标680769
评论输入框2931187
发送(键盘打开)643724
发送(键盘关闭)6321217

互动操作

元素XY
点赞图标666629
收藏图标664823

发布操作

元素XY
创建 (+)3601230
从相册选择671212
第一个视频123355
下一步按钮5261217
描述输入框55177
关闭键盘525528
发布按钮5211210

智能 UI 识别

机器人使用 uiautomator dump 动态检测图标位置:

  1. 导出当前 UI 层级
  2. 搜索关键词("like"、"favorite")
  3. 返回匹配元素的中心坐标
  4. 检测失败时回退到固定坐标

这确保了在不同 TikTok UI 布局中的可靠性。

性能

耗时

  • 评论: 每个视频约 20-30 秒
  • 点赞 + 收藏: 每个视频约 5-8 秒
  • 发布: 约 30-60 秒(取决于下载)

成功率

  • 智能 UI 识别: 95%+
  • 备用坐标: 90%+

故障排除

设备未找到

adb kill-server
adb start-server
adb devices

点赞/收藏点击错误图标

  1. 智能 UI 识别应处理变体
  2. 如需要更新备用坐标

发布失败

  1. 验证视频下载成功
  2. 检查媒体扫描完成
  3. 手动清理相册

最佳实践

速率限制

  • 每账户每天最多 25-30 条评论
  • 间隔会话: 每天一次,时间要变化
  • 休息: 每周跳过 1-2 天
  • 监控: 注意限流迹象

账户安全

  • 账户年龄: 自动化前至少 7 天
  • 先手动活动: 先点赞、关注、自然浏览
  • 从小开始: 先测试 3-5 个视频

项目结构

tiktok-android/
├── SKILL.md                           # 本文件
├── README.md                          # 完整文档
├── tiktok_bot.py                     # 主 CLI 入口
├── src/
│   └── bot/
│       └── android/
│           ├── tiktok_android_bot.py  # 核心自动化
│           └── tiktok_navigation.py   # 导航流程
└── data/                             # 日志

示例

搜索 + 评论

python3 tiktok_bot.py search --topics fitness --videos 3

探索推荐页

python3 tiktok_bot.py explore --videos 5

互动模式(点赞 + 收藏 + 评论)

python3 tiktok_bot.py interact --videos 3 --like --favorite --comment --topics travel

发布视频

python3 tiktok_bot.py publish --video "/path/to/video.mp4" --description "我的 TikTok 视频 #fyp"

依赖

loguru>=0.7.0
anthropic>=0.18.0
openai>=1.12.0

ADB 必须已安装并在 PATH 中。

许可证

MIT - 负责任地使用。自动化评论可能违反 TikTok 服务条款。


状态: 生产就绪,具备智能 UI 识别。✅

最后更新: 2026 年 3 月 27 日(新增 AI 智能评论、交互式设置向导说明)

Comments

Loading comments...