creatok-recreate-video

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-supplied TikTok content via runAnalyzeVideo (lib/creatok-client.js calling /api/open/skills/analyze with the provided tiktokUrl), writes the transcript/vision into outputs/recreate_source.json, and instructs the model to read and base creative and generation decisions on those artifacts—i.e., untrusted, user-generated third‑party content is read and can materially influence actions.