fiction-studio

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow ingests outsider-authored free text directly from the author/user by reading the user’s prompts and then loading the user-created project files (e.g., premise.md, outline.md, characters/*.md, world-bible.md, scene-list.md, manuscript/*.md) that later phases read and edit.