Extract structured data from websites with sanitized Markdown output.
npx skills add https://github.com/ouakar/ubinarys-dental --skill web-scraper-ouakar
Please help me install this Agent Skill. Skill: web-scraper Source: https://github.com/ouakar/ubinarys-dental/tree/main/skills/forgewright/skills/web-scraper Command: npx skills add https://github.com/ouakar/ubinarys-dental --skill web-scraper-ouakar
Web Scraper — Security-First Data Extraction Specialist addresses the challenge of obtaining clean, structured data from websites without compromising security or data integrity. It enforces strict safeguards (library-mode only, URL validation, SSRF protection, output sanitization, and non-persistent browser state) to prevent data leakage and prompt injection while enabling reliable downstream ingestion.
Run a secure crawl against a target URL and produce sanitized output ready for downstream processing.
High-intent search queries and answers about installing and using this skill.
Secure web scraping extracts structured content using library-mode crawling, enforcing URL validation and output sanitization to prevent data leakage. It produces clean, sanitized Markdown or JSON feeds ready for RAG workflows and downstream LLM synthesis.
Library-mode web crawling operates without Docker API exposure, reducing security risks by running crawlers directly in the environment. This approach enforces strict browser isolation and hardened config defaults to prevent prompt injection and data exfiltration during data extraction.
Web scraping prevents SSRF and prompt injection through strict URL validation, output sanitization, and non-persistent browser state. These security constraints ensure that malicious content from target sites cannot execute arbitrary commands or access internal network resources.
Yes, web scraping supports Markdown extraction when site structure is unknown, delivering sanitized Markdown output optimized for RAG workflows. CSS and XPath-based extraction are also available for pulling structured data like product specs into clean JSON feeds.
Secure web scraping enforces rate limiting and hardened browser isolation by default to ensure reproducible data pipelines. Non-persistent browser state guarantees that each crawl session remains isolated, preventing cross-session data contamination and ensuring stable data extraction.
Library-only web crawling limitations include reliance on strict URL validation and rate limiting, which may restrict aggressive crawling. It avoids Docker API usage entirely, meaning all extraction must conform to library-mode constraints without bypassing security boundaries for high-volume scraping.
aryaniyapsConfigure Firecrawl credentials and install SDKs for web crawling projects.
Lucius646Manage Markdown-based knowledge bases with LLM-driven ingestion, querying, and maintenance.
wsbaserConstruct XCSS selectors from HTML markup and CSS/XPath for UnionInit attributes.
ggombeeGenerate Playwright web crawler code templates for scraping tasks.
