humanize-image-generation

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only ingests first-party/bundled skill instructions and the user’s provided brief/images (and optionally uses an allowed external research capability to inspect original source pages); there is no required runtime path that unpromptedly consumes outsider-authored free text from inboxes/feeds/tickets/issue bodies or arbitrary URLs.