recipe-front-adjust

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the ui-analyzer to "fetch external UI sources via the declared access methods" (Step 2 prompt) and requires verification against design origins using methods like "WebFetch from a public URL" or "Storybook URL" (Step 5), so the agent will read and act on external public/untrusted content that can influence edits and verification decisions.