brand-voice

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

• Third-party content exposure detected (high risk: 0.90). This skill's Collection Workflow explicitly requires pulling public, user-generated sources (e.g., "recent original X posts" via x-api and public site copy/ECC landing page) and mandates the agent read and extract style from them to build voice profiles that will drive downstream actions, so untrusted third-party content can materially influence behavior.