creating-engineer-manga

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

• Third-party content exposure detected (high risk: 0.90). The skill's PROMPT_TEMPLATE.md and PATTERNS.md explicitly require attaching or uploading user-provided images (e.g., "必ずキャラクターの元画像を一緒に添付してください" and the "ラフ画を写真に撮ってアップロード" flow), so the agent will ingest untrusted user-generated content as part of its workflow.