landing-page-design

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Implementation Workflow" Phase 1 ("Gather 5-10 hero screenshots as wireframes") and its "Design Resources" explicitly point to public sites (Dribbble, Awwwards, Superhero.design, Google Fonts, Iconify, etc.), requiring the agent to fetch and interpret untrusted, user-generated web content as part of the workflow, which can materially influence design decisions and subsequent actions.