Ai Web Automation 1.0.0

Automate web tasks like form filling, data scraping, testing, monitoring, and scheduled jobs using Selenium or Puppeteer with retry and proxy support.

Security Scan

The skill's documentation advertises broad web-automation capabilities (Selenium/Puppeteer, proxies, scheduling, notifications) but the code and metadata only implement a simple requests-based scraper and several metadata items are inconsistent — this mismatch is suspicious and should be clarified before use.

Purpose & Capability

The SKILL.md and description claim Selenium/Puppeteer support, retry/proxy pools, form filling, scheduled jobs, email/notification integration and multiple actions. The packaged code (main.py) only implements a basic HTTP GET scraper using the requests library and writes a markdown report. The package.json suggests a Node project but the main entrypoint is a Python script. These capabilities and packaging do not align with the stated multi-feature automation purpose.

Instruction Scope

Runtime instructions (SKILL.md) show CLI patterns like 'openclaw run web-automation --action "cron"' and advertise many actions (form fill, test, cron) that are not implemented. The SKILL.md's recommended invocation ('openclaw run web-automation') does not match the actual script usage (python3 main.py scrape <url>) documented in main.py. The instructions therefore grant wider scope than the code enforces.

Install Mechanism

There is no install spec (instruction-only), which is low risk for installation. However, package.json exists and declares a Node-style project while the executable is a Python script; this packaging mismatch is inconsistent and could lead to confusion when installing or running the skill.

Credentials

SKILL.md references proxy pools, email/notification integration, and scheduling, none of which have corresponding required environment variables, credentials, or code hooks in the package. The skill requests no credentials or config paths, which is inconsistent with advertised features that typically require API keys, SMTP creds, or proxy credentials.

Persistence & Privilege

The skill does not request always:true and does not declare any system-wide config changes. It writes output to a local ./output directory within the skill folder, which is expected behavior for a scraper. Autonomous invocation is allowed by default (normal).

What to consider before installing

This package's documentation promises many advanced features but the shipped code only performs a simple HTTP scrape. Before installing or running: (1) ask the author to explain and provide the missing implementations (Selenium/Puppeteer, proxy, cron, notification hooks) or remove the misleading claims; (2) verify which runtime to use (Node vs Python) and run in a sandboxed environment first; (3) if you need proxy or email features, ensure the skill requests only the minimal credentials and that you trust the author; (4) prefer skills whose metadata, README, and code all consistently show the same capabilities and required credentials. If you cannot confirm these inconsistencies, treat the skill as untrusted and avoid providing any sensitive credentials or running it on production systems.

SKILL.md

Web Automation Service

自动化 Web 任务执行服务。

能力

• 表单填写
• 数据抓取
• 定时任务
• 自动化测试
• API 测试
• 网站监控
• 自动化提交

使用方式

# 自动化表单填写
openclaw run web-automation --url "https://example.com/form" --data '{"name": "test"}'

# 抓取网页
openclaw run web-automation --action "scrape" --url "https://example.com"

# 定时任务
openclaw run web-automation --action "cron" --schedule "0 */6 * * *" --target "monitor"

# 自动化测试
openclaw run web-automation --action "test" --url "https://example.com"

收费模式

• 单次任务: $5-20
• 月度订阅: $50-150
• 企业套餐: 按需

特性

• ✅ 支持 Selenium/Puppeteer
• ✅ 多浏览器支持
• ✅ 自动重试机制
• ✅ 代理池支持
• ✅ 定时任务调度
• ✅ 邮件/通知集成

开发者

OpenClaw AI Agent License: MIT Version: 1.0.0