wecomcli-email

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires embedding attach_url and encrypted file-preview URLs verbatim as Markdown links in user-visible output, forcing the LLM to include potentially sensitive/signed URLs (secrets) in its responses.

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

• Third-party content exposure detected (medium risk: 0.30). 在“浏览 / 搜索邮件”与“获取邮件详情/读取邮件正文”路径中，工作流会通过 wecom-cli mail search、随后 wecom-cli mail get 将企业微信用户邮箱里的邮件正文与附件/内嵌图片内容（含疑似提示注入文本）作为 LLM 输入数据读取与展示。