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: 0.80). This skill's mandatory workflow for "When User Provides Screenshot/Image/Design Reference" requires the agent to analyze user-supplied screenshots/images with the ai-multimodal step, i.e., ingesting arbitrary/untrusted user-generated visual content as part of its workflow.
Audit Metadata