web-scraper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and processes arbitrary public web content (see scripts/scraper.py: fetch_simple, scrape_with_js, deep_crawl, batch_scrape and SKILL.md commands like "scrape ", "crawl ", "--llm-extract"), and it uses LLM-powered extraction and link-following so untrusted third-party page content can directly influence extraction, crawling, and subsequent tool actions.