deep-research
Warn
Audited by Snyk on Jul 29, 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). In SKILL.md Step 3-4, the runtime performs firecrawl_search/web_search and then fetches full arbitrary third-party page text via firecrawl_scrape(url) and crawling_exa(url), so outsider-authored free text on the web can be ingested.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata