peach-review-ux

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly accepts URLs and instructs the agent to "브라우저/HTML 내용을 확인하고 화면 흐름을 검토" and in Workflow step 1 states "URL이면 페이지 목적... 먼저 파악한다", meaning the agent will fetch and read arbitrary public web pages and use their content to drive UX review decisions, which meets the criteria for exposure to untrusted third-party content.