Agent-Media UGC Playbook

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path is a single API call to POST https://api.agent-media.ai/v1/skills/make_ugc/run with user-provided fields like script (and optional URLs), so outsider-authored free text is directly ingested by the workflow as the content to generate a video.