Web Scraper Jina

Bypass Cloudflare and scrape any website using r.jina.ai API. Works on sites with strong protection like Truth Social, Cloudflare Turnstile, etc.

This skill is essentially a short how-to that tells the agent to use a third-party scraping proxy (r.jina.ai) to fetch pages, including ones protected by anti-bot measures. Before installing, consider: 1) provenance — the publisher and homepage are unknown; that increases trust risk; 2) legality and ToS — intentionally circumventing protections can violate site terms of service or laws in some jurisdictions; 3) privacy — fetched content may include private data or trigger rate-limiting/blocks on your account; 4) dependency on a third-party proxy — your requests go through r.jina.ai, so review their terms and privacy policy; 5) safer alternatives — prefer official APIs, site-provided feeds, or getting explicit permission. If you still want to use it, avoid supplying credentials, limit use to public content you have permission to access, and test in a controlled environment. If you need higher assurance, ask the publisher for provenance or request a version that uses a maintainer-trusted backend or official APIs.

Type: OpenClaw Skill Name: web-scraper-jina Version: 1.0.1 The skill provides instructions and code snippets for using the r.jina.ai API to scrape web content and bypass anti-bot protections like Cloudflare. The content in SKILL.md and the Python example are consistent with the stated purpose of web scraping and do not contain any evidence of data exfiltration, malicious execution, or prompt injection attacks.