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 skill run path POST https://api.agent-media.ai/v1/skills/make_ugc/run ingests first-party request fields like script (and optionally broll_url/image/character) which are free text authored by the provider user, so an outsider can supply arbitrary text that the LLM will consume at runtime.