firecrawl-scraper

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests content from arbitrary public websites via the Firecrawl API (endpoints like /scrape, /crawl, /extract, /search, /batch/scrape) — e.g., it cites crawling https://docs.stripe.com/api and competitor sites — and the agent is expected to read and process that untrusted third-party content.