info-card-designer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and processes external URLs and user-provided web content (see README "Give Claude a URL" and usage examples like "把这个链接做成信息卡 https://wise.readwise.io/..."), and the workflow requires the agent to extract and transform that untrusted third‑party content into the card (SKILL.md: "卡片内容必须 100% 来自用户提供的原文/URL/文本"), so third‑party page contents can directly influence generation and tool actions.