firecrawl

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow ingests outsider-controlled free text only through URLs/outputs provided by the user (e.g., “Apply this gate before every URL-bearing command… including every URL discovered by search, map, crawl…”) and then requires strict HTTPS/DNS/redirect validation before invoking Firecrawl CLI; it does not read arbitrary outsider-authored text sources without a specific selected URL-bearing item.