animated-landing-workflow

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

• Third-party content exposure detected (high risk: 0.90). This skill's pipeline explicitly instructs the agent to browse and ingest public, user-generated sources (e.g., land-book, Dribbble, motionsites.ai, higgsfield.io) as required inputs (Stages 1–4) and to use those references to drive prototype design and handoff decisions in Claude Design/Claude Code, which allows untrusted third-party content to materially influence tool actions and prompts.