mvmaker-h3-skill

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow only ingests outsider-authored free text indirectly via user-supplied prompt/material fields (e.g., lyrics/title/style references) that are passed into the director and then into h3-prompt-writing as part of the official H3 prompt generation; there is no reading of an external outsider-authored feed/queue without selecting specific user-provided items.