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.

Security Scan

The skill is internally coherent (it just instructs the agent to use r.jina.ai to fetch pages) but it explicitly encourages bypassing access protections and comes from an unknown source with no provenance, which raises legal/abuse and trust concerns.

Purpose & Capability

The name/description match the SKILL.md: the skill simply tells the agent to prepend https://r.jina.ai/ to target URLs to retrieve content. The functionality claimed (scraping protected sites) is entirely delegated to the third-party r.jina.ai service; the skill itself has no code, installs, or extra credentials.

Instruction Scope

The instructions explicitly advise bypassing Cloudflare, Turnstile, and other protections and list targeted sites (Truth Social, etc.). While the instructions do not request local files, credentials, or system access, they directly instruct circumvention of access controls and encourage potentially terms-violating or illegal scraping behavior.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by the skill itself, which is low technical risk in terms of install mechanism.

Credentials

No environment variables, credentials, or config paths are requested — the skill does not ask for secrets or unrelated permissions.

Persistence & Privilege

No elevated privileges or always-on behavior requested (always: false). The skill does not attempt to modify other skills or system settings.

What to consider before installing

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.

Web Scraper using r.jina.ai

Bypass Cloudflare and scrape any website using free r.jina.ai API.

Features

• Bypass Cloudflare, Turnstile, and other protections
• Works on Truth Social, Bitget, and other protected sites
• Returns clean Markdown content
• Free to use

Usage

Simply prepend https://r.jina.ai/ to any URL:

https://r.jina.ai/https://truthsocial.com/@realDonaldTrump
https://r.jina.ai/https://bitget.com/events/poolx

Examples

Get Trump Truth Social posts:

curl -s "https://r.jina.ai/https://truthsocial.com/@realDonaldTrump"

Get any protected page:

curl -s "https://r.jina.ai/https://example.com"

In Code

import requests

def scrape(url):
    return requests.get(f"https://r.jina.ai/{url}").text

Use Cases

• Scrape Truth Social, Gab, Gettr
• Bypass Cloudflare protected sites
• Extract content from news articles
• Monitor competitors