Ai Web Automation Local

PassAudited by ClawScan on May 1, 2026.

Overview

The included code is a simple user-directed web scraper, but the documentation overstates broader automation features and has minor provenance/dependency inconsistencies.

This appears safe as a basic web-page status/title scraper, but do not assume it supports the broader advertised browser automation, scheduling, proxy, or notification features. Verify URLs before scraping and confirm the package identity if you plan to depend on it.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI02: Tool Misuse and Exploitation

What this means

If given the wrong URL, the skill could make unintended requests, including to sites the user did not mean to contact.

Why it was flagged

The script fetches an arbitrary command-line URL. This is expected for web scraping, but it means the skill can initiate network requests to user-chosen sites.

Skill content

url = sys.argv[2]
...
response = requests.get(url, timeout=10)

Recommendation

Only run it against websites you are authorized to access, and verify the target URL before invoking the scraper.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

Users may expect scheduling, form submission, Selenium/Puppeteer, proxy, or notification features that are not present in the supplied implementation.

Why it was flagged

The documentation advertises broad automation capabilities, while the provided main.py only supports the scrape action. This could mislead users about what the skill actually does.

Skill content

- 表单填写
- 数据抓取
- 定时任务
- 自动化测试
...
- 自动化提交
...
- ✅ 支持 Selenium/Puppeteer
- ✅ 代理池支持

Recommendation

Treat this as a simple scraper unless the developer provides matching implementation and setup instructions for the advertised features.

Info

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

It may be harder to verify the publisher or confirm that this package corresponds exactly to the listed registry entry.

Why it was flagged

The bundled metadata does not match the registry metadata shown for this evaluation, which lists a different owner ID and slug. This is a provenance inconsistency, though no malicious code is shown.

Skill content

"ownerId": "kn7dbjjarnfjy3g0q24zdkmg4581gmrm",
  "slug": "ai-web-automation"

Recommendation

Verify the publisher and package identity before relying on it, especially if future versions add real browser automation or credentialed workflows.