skill-converter

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

• Third-party content exposure detected (high risk: 1.00). Step 2 explicitly says the skill will "利用してインターネット検索を利用して...最新使用を取得する", meaning the agent will fetch and interpret internet search results / public web specifications (untrusted third‑party content) as part of its workflow.