website-building

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to "Search the web for reference sites" and "Fetch any URLs the user provides" and to load assets/models from external CDN URLs (see "Use Every Tool" and the "Workflow" and "Asset Loading Strategy" sections of SKILL.md), so it ingests arbitrary public third-party content that can influence design decisions and tool actions.