context-to-video

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via the “ブログ/記事 URL” path: web_fetch fetches arbitrary public web page text at runtime, which is then summarized/structured by the caller LLM into notes/script.json (indirect prompt injection risk through fetched page content).