promo-brief

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:13-15 指定在运行时从“GitHub URL/官网 URL/产品文档 URL”抓取 README、首页文案、功能列表、定价、截图文字与文档内容等网页/文档自由文本，并将其用于“提炼卖点和目标受众/输出创意简报”，属于公共网页等外部来源的运行时文本注入风险。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches external content at runtime from user-supplied URLs (e.g., "GitHub URL", "官网 URL", "产品文档 URL") and injects README/homepage/API docs into the agent's context to generate the brief, so remote content can directly control prompts.