design-concepts

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (Step 3: "Inspiration & Research") explicitly instructs the agent to perform web_search/web_fetch and gather references from public, user-generated sites like Dribbble, Behance, and Awwwards, meaning the agent will ingest untrusted third-party content that can influence design decisions and subsequent actions.