aesthetic
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Workflow 1 explicitly instructs browsing public inspiration sites (Dribbble, Mobbin, Behance, Awwwards) and using chrome-devtools to capture screenshots that the ai‑multimodal component analyzes, so the agent ingests untrusted, user-generated web content.
Audit Metadata