website-rebuild-skill
复刻网站的 Agent Skill：抓只读镜像、从压缩代码逐行还原、自动比对验收。An agent skill that mirrors a website, rebuilds it from the minified code, and verifies the result with automated diffs.
No outside reports on file
This tool can download and rebuild malicious code automatically, making it risky unless you fully control which sites it copies and you inspect results before using them.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (boyang-hu/website-rebuild-skill)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/boyang-hu/website-rebuild-skill ↗
About Website Rebuild Skill
This skill lets an AI agent copy a website by downloading a read-only snapshot, unpacking minified (compressed) code line-by-line, and automatically checking that the rebuilt version matches the original. It's designed to create exact digital replicas of web pages for comparison or archival.
Who it’s for
Developers or AI systems that need to verify website copies are accurate, compare code changes, or archive web content. This is a specialized tool for technical teams, not general users.
Alternatives
- Wget or curl: Simple command-line tools to download website snapshots without unpacking minified code.
- Puppeteer or Playwright: Headless browser tools that can screenshot or archive sites with JavaScript rendering.
- Archive.org Wayback Machine API: Retrieves publicly archived versions of websites from a trusted third party.
- Git-based site generators (Hugo, Jekyll): For rebuilding static sites from source, not minified mirrors.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/boyang-hu/website-rebuild-skill (opens external site) for installation and configuration instructions.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.6k
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-28).
Risks to watch for
- Downloading untrusted sites: Fetching any website means downloading potentially malicious HTML, JavaScript, or files that could contain exploit code.
- Minified code deception: Attackers can hide malware in compressed code that looks harmless when unpacked; the AI might not detect it.
- Legal issues: Copying websites without permission may violate copyright or terms of service; the skill doesn't check if copying is allowed.
- Data leakage: If the agent processes pages containing API keys, passwords, or private data in HTML/JavaScript, those secrets could be exposed or logged.
- Mirror abuse: A copied site could be re-hosted to impersonate the original or spread phishing attacks.
How to lower the risk
Least-privilege permissions
- Only connect to known, trusted websites you own or have explicit permission to copy.
- Run the skill with minimal file system and network access.
Network isolation
- Use a firewall to block outbound traffic except to approved domains.
- Never allow the agent to fetch from user-supplied URLs without review.
Monitoring
- Log all websites downloaded and rebuilt; review them regularly.
- Alert if unexpected domains are accessed or file sizes are unusual.
Red flags to watch for
- Site content that suddenly changes or includes new JavaScript.
- Rebuild process that takes much longer than expected (possible hidden loops).
- Downloaded files larger than the original site suggests.
Questions
How do I install Website Rebuild Skill?
Website Rebuild Skill does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/boyang-hu/website-rebuild-skill.
Are there security reports about Website Rebuild Skill?
No reports found for this package in our research (last checked 2026-10-28). Website Rebuild Skill currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include downloading untrusted sites, minified code deception, legal issues.
Is Website Rebuild Skill actively maintained?
Website Rebuild Skill has 1.6k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/boyang-hu/website-rebuild-skill before pinning it in production.
What are alternatives to Website Rebuild Skill?
Notable alternatives to Website Rebuild Skill include Wget or curl (Simple command-line tools to download website snapshots without unpacking minified code), Puppeteer or Playwright (Headless browser tools that can screenshot or archive sites with JavaScript rendering), Archive.org Wayback Machine API (Retrieves publicly archived versions of websites from a trusted third party), Git-based site generators (Hugo, Jekyll) (For rebuilding static sites from source, not minified mirrors). You can also compare Website Rebuild Skill side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Website Rebuild Skill? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/boyang-hu-website-rebuild-skill)HTML embed:
<a href="https://agentarmorhq.com/skills/boyang-hu-website-rebuild-skill"><img src="https://agentarmorhq.com/api/badge/boyang-hu-website-rebuild-skill" alt="AgentArmorHQ Risk Grade for Website Rebuild Skill" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "boyang-hu-website-rebuild-skill"- Compare Website Rebuild Skill →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use website-rebuild-skill? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: website-rebuild-skill
- **Listing URL:** https://agentarmorhq.com/skills/boyang-hu-website-rebuild-skill
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.6k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (boyang-hu/website-rebuild-skill)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/boyang-hu/website-rebuild-skill
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- boyang-hu
- Source code
- github.com/boyang-hu/website-rebuild-skill
- Est. context load
- ~70 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 1.6k GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-22
Community
Discussions for Website Rebuild Skill
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude