自动周报助手

自动整理周报工具。支持从多个数据源（GitHub、飞书文档、日历）汇总工作内容，生成Markdown周报。支持保存历史、AI摘要、导出PDF/HTML、发送邮件、写入飞书文档。适用于需要定期总结工作成果的用户。

This skill appears to do what it claims, but review these before installing/using: 1) Credentials: the scripts require GitHub/Feishu/SMTP/Google credentials even though the registry metadata lists none — supply tokens securely (prefer environment variables or a secrets store, not raw CLI args) and avoid embedding passwords in shell history. 2) Local storage: reports and metadata are saved under ~/.weekly-report/history/ — check permissions and clean sensitive contents if needed. 3) Dependencies: ensure Python packages (requests, PyGithub, googleapiclient) and optional tools (pandoc, xelatex) are installed in a controlled environment. 4) Bugs: there are minor code bugs (incorrect datetime.timedelta usage in history_manager) you may want to fix before automated runs. 5) Least privilege: create and use scoped API tokens (short-lived or limited-permission tokens) and revoke them if you stop using the skill. If you want, I can point out exact lines to change for safer credential handling or help produce hardened example usage (env var approach, prompting for secrets, file-permissions).

Type: OpenClaw Skill Name: weekly-report-ai Version: 1.0.0 The skill bundle is a functional weekly report generator that aggregates data from GitHub, Feishu, and Google Calendar. It is classified as suspicious because it possesses several high-risk capabilities that, while aligned with its stated purpose, present a significant attack surface. These include sending emails via SMTP using user-provided credentials (email_sender.py), executing external shell commands via subprocess for PDF conversion (export_pdf.py), and performing local filesystem writes for history management (history_manager.py). No evidence of intentional malice or data exfiltration was found, but the scripts lack robust input sanitization, such as in the regex-based Markdown-to-HTML conversion which is vulnerable to XSS, and the potential for path traversal in history management.