web-scraper
100 / 100 · Low risk
Fine to try.
Scrape web pages, crawl sites, extract structured data, and capture screenshots through SandBase. Use when asked to extract content from URLs, crawl websites, get structured data from pages, take screenshots, or convert web pages to markdown.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'web-scraper' ] || [ -L ~/.agents/skills/'web-scraper' ]; then echo 'A skill folder named web-scraper already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/sandbaseai/sandbase-skills' "$d" && git -C "$d" checkout --quiet 'cbab58188611e626ccaf54ac346b437d12ea4729' -- 'research/web-scraper' && mkdir -p ~/.agents/skills && cp -R "$d"/'research/web-scraper' ~/.agents/skills/'web-scraper' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'web-scraper' ~/.claude/skills/'web-scraper' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/sandbaseai/sandbase-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | cbab581 | 100 |