realistic-ugc-video

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly accepts and passes arbitrary image URLs into spawned background agents ("prompt: [Include image URL, script chunk, movement prompt, output path]") and references external services (e.g., infinitetalk.ai, Resemble AI), meaning the agent will ingest and act on untrusted third‑party/user‑provided content (images and external API outputs) as part of runtime processing.