firecrawl-build-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to use Firecrawl’s /search to discover and optionally "hydrate" current web results (public webpages) as part of the workflow, meaning the agent will fetch and read untrusted third-party web content that can drive downstream scraping and actions.