design
Warn
Audited by Snyk on Feb 27, 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 CREATE mode explicitly instructs the agent to "Analyze the design system at [URL]" (SKILL.md, "From URL (Reference App)"), meaning it fetches and interprets live public websites (untrusted third-party content) to generate design-system.md and drive subsequent actions.
Audit Metadata