frontend-design
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: 0.90). The skill's mandatory workflow for screenshot/image/design inputs explicitly instructs the agent to analyze user-provided screenshots/images with the ai-multimodal skill (./references/design-extraction-overview.md), so it ingests and interprets untrusted third-party user-generated visual content.
Audit Metadata