legal-text-format

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly describes a required workflow where the agent ingests content fetched from public third-party sources (e.g., "用户提供微信公众号链接 → AI 使用 wechat-article-fetch 抓取 → AI 调用 legal-text-format 格式化" in the "典型工作流程"), so the skill processes untrusted web/WeChat article content as part of its normal operation and could be influenced by embedded instructions.