kitchen-sink-design-system
Warn
Audited by Snyk on Apr 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: 0.70). The skill's Phase 3 (Image & Illustration) and references/image-reinterpretation.md explicitly instruct the agent to "Find Reference Photo" and to consume external design inspiration via companion skills (design-lookup, deep-research, openai-image), i.e., ingesting public/third‑party images and web-sourced content that the agent must read and use to compose generation prompts and actions — meeting the criteria for untrusted third‑party input.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata