brand-to-design-md

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to open/fetch and analyze public brand URLs, official homepages, press/press-kit pages, public CSS, SVG logos and images (see "Gather Evidence" in SKILL.md and the "Official URL opened or fetched" item in references/workflow-checklist.md), which are untrusted third-party web sources that the agent must read and that materially drive its subsequent decisions and demo generation.