product-frontend-design
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts “design reviews of existing sites” and states the user may provide “a live URL,” meaning the agent is expected to fetch and analyze arbitrary public websites (untrusted third-party content) as part of its workflow.
Audit Metadata