edgespark-frontend-design

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

• Third-party content exposure detected (high risk: 0.70). The skill's "Content Authenticity" section in references/design-principles.md explicitly directs the agent to "proactively search for real imagery" using stock-image, entity-aware, and design-inspiration searches, which requires fetching and evaluating open/public third-party (potentially user-generated) content that can influence design choices and subsequent actions.