firecrawl-web
Warn
Audited by Snyk on Aug 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The firecrawl-web skill ingests outsider-authored free text at runtime by scraping user-supplied URLs (e.g., the
markdown/extract/crawlcommands callapp.scrape(... formats=["markdown"]or JSON extraction and print the resulting markdown/text back to the agent), so an outsider can cause the agent to read arbitrary web page content they author.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata