scrape-explore-site
Warn
Audited by Snyk on Jun 26, 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). The skill downloads and renders outsider-authored web pages at runtime (public URLs provided via
$ARGUMENTS), then reads their HTML text (rendered.html/raw.html) into the LLM context during link extraction/classification, enabling indirect prompt injection via page body content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata