ScrapingBee Fetch

Advanced JavaScript web page renderer using ScrapingBee API. Extracts main content and returns clean Markdown.

Security Scan

The skill's code, instructions, and required credential align with its stated purpose (using the ScrapingBee API to render pages and extract content); nothing in the files suggests behavior outside that purpose.

Purpose & Capability

The name/description (ScrapingBee renderer + Markdown extraction) match the code and runtime instructions. Minor inconsistency: the registry metadata at the top says "Required env vars: none", while SKILL.md and fetch.py require SCRAPINGBEE_API_KEY — the key is appropriate and needed for the declared purpose.

Instruction Scope

SKILL.md directs the agent to set SCRAPINGBEE_API_KEY and call the included fetch.py with URL and options. The script only reads .env (via python-dotenv), the SCRAPINGBEE_API_KEY env var, and sends requests to ScrapingBee's API endpoint; it does not read unrelated files or exfiltrate data to unexpected endpoints.

Install Mechanism

No install spec is provided (instruction-only + a bundled script). Dependencies are standard (requests, python-dotenv) and the script runs locally; no downloads from untrusted URLs or archive extraction are present.

Credentials

Only SCRAPINGBEE_API_KEY is required and the script enforces its presence — this is proportional. Note the inconsistency where registry metadata omitted this requirement while SKILL.md declares it; verify you supply a valid ScrapingBee key and store it safely (e.g., .env or process env).

Persistence & Privilege

always:false and no special privileges are requested. The skill does not attempt to modify other skills or system-wide settings.

Assessment

This skill appears to do exactly what it claims: it sends the target URL (and options) to ScrapingBee and prints the extracted title and text. Before installing, verify you trust ScrapingBee (requests to a third‑party service mean the target URL and scraped content will be sent to that service). Provide the SCRAPINGBEE_API_KEY only if you accept that use, and store it securely (avoid committing .env to version control). Note the small metadata mismatch: the registry summary omitted the required env var; confirm the presence and legitimacy of the API key and consider running the script in an isolated environment or sandbox for additional assurance. Also ensure your web scraping complies with the target sites' terms of service and applicable law.

Use this skill to render JavaScript on target websites and extract the main content. It returns clean Markdown optimized for LLM reading.

Setup

You need a ScrapingBee API key to use this skill. Set it as an environment variable:

export SCRAPINGBEE_API_KEY="your_api_key_here"

Or add it to a .env file in the directory where you run the script.

Usage

uv run fetch.py --url "https://example.com"

Optional Parameters

• --no-render-js: Disable JavaScript rendering (faster, but might miss dynamic content).
• --country-code <code>: Use a proxy from a specific country (e.g., us, uk, ru).
• --wait <milliseconds>: Wait time in milliseconds before extracting content (default: 3000).
• --no-block-ads: Disable ad blocking (ads are blocked by default to save bandwidth and speed up rendering).
• --premium-proxy: Use a premium proxy (useful for highly protected websites).

Examples

Fetch a website using a US proxy and wait 5 seconds:

uv run fetch.py --url "https://example.com" --country-code us --wait 5000

Fetch a highly protected website using a premium proxy:

uv run fetch.py --url "https://example.com" --premium-proxy

Fetch a simple website without rendering JavaScript:

uv run fetch.py --url "https://example.com" --no-render-js