content-refresher

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow repeatedly asks for and uses external/public URLs and competitor research (e.g., "Refresh this article for [current year]: [URL/content]", "Update this content to outrank [competitor URL]", and the Pre-Refresh/Validation steps that mandate competitor URLs and source updates), which means the agent is expected to fetch and interpret untrusted third-party web content that can influence its recommendations and actions.