ai-media

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests user-provided narration text (script → ElevenLabs text_to_speech.convert(text=...)) and may also ingest user-provided scene prompts via the delegated “one prompt per scene” flow, so outsider-authored free text is directly passed to the LLM-capable external model calls.