media-production

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows explicitly instruct agents to perform web searches and ingest remote, user/website-sourced materials (e.g., references/podcast-studio.md's "웹 검색으로 인용된 수치...", references/youtube-production.md's "경쟁 채널 분석" via web search, and Remotion guides that fetch external Lottie/ElevenLabs resources), meaning untrusted third‑party content is read and used to shape scripts, durations, and follow-up actions.