firecrawl-scraping

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

• Third-party content exposure detected (high risk: 1.00). The skill (see scripts/firecrawl_scrape.py and references/single-page.md / references/website-crawler.md) explicitly fetches and ingests arbitrary public URLs via the Firecrawl API (POST https://api.firecrawl.dev/v2/scrape and /v1/crawl), and SKILL.md plus the integration patterns show that scraped, untrusted webpage content is then consumed by downstream analysis and automation (RAG, CRM enrichment, content generation), so third-party pages can materially influence agent decisions.