firecrawl-search
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This skill performs runtime web search and, with
--scrape, fetches and ingests full page text from arbitrary public URLs into the agent’s LLM context (outsider-authored web content via search→scrape).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata