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 SKILL.md CREATE mode ("From URL (Reference App)") explicitly instructs the agent to analyze a live app at an arbitrary URL and extract its design system, meaning it fetches and interprets public/untrusted web pages whose content can directly influence the agent's subsequent design decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:16 AM