visual-ralph
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and captures live URL-derived references (see "Establish the visual reference" and the live URL workflow that requires "source URL and permission/scope note" and a captured baseline screenshot), meaning it ingests arbitrary public web pages as authoritative inputs that directly drive implementation and tooling decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata