story-import

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

• Third-party content exposure detected (medium risk: 0.30). source text from outsider authors is ingested at runtime via Phase 1 Step 3/Step 4 into the full analyze pipelines (e.g., user-provided pasted text or source file is saved then story-long-analyze/story-short-analyze runs, producing 拆文库/{导入书名}/); this is free-form user content that the required workflow will read before producing downstream artifacts.