firecrawl-scraper

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime path calls Firecrawl with user-supplied url/urls (e.g., /v2/scrape, /v2/batch/scrape), and Firecrawl returns scraped page text/markdown in the sub-skill output (firecrawl-api.cjs parses response JSON and prints data), which is then ingested into the agent context—this is outsider-authored web content.