getting-started

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs searching, inspecting, and installing publicly published snippets (e.g., "公開されている snippet を利用したい" and the commands mir search / mir info / mir install), which involves fetching and acting on untrusted, user-generated third-party content that could influence subsequent actions.