eye
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). Step 1 instructs the skill to “Navigate to the page / localhost / URL” and “Screenshot the target area,” which implies runtime browser fetching/DOM extraction of the page’s visible text (outsider-authored web content) into the LLM context for review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata