微信公众号监控

微信公众号调研 + 监控 + 报告推送。每个产品独立目录，互不影响。

This skill appears to do what it says: it calls an external service (https://down.mptext.top) using an API key, checks articles, and writes per‑product reports in ~/.openclaw/workspace/wechat-monitor/. Before installing: 1) Confirm you trust the mptext.top service (its privacy/security and what data it stores). 2) Do not hardcode your API key into monitor.py — prefer setting MPTEXT_API_KEY in your environment. 3) Note the registry metadata did not declare the required env var (MPTEXT_API_KEY); expect to provide that secret manually. 4) Inspect any accounts.json created and the reports folder to ensure no sensitive data is being gathered or stored. If you’re uncomfortable with the external API, consider replacing it with a different data source or running the script in a restricted environment.

Type: OpenClaw Skill Name: wechat-monitor Version: 1.0.0 The skill bundle provides a legitimate tool for researching and monitoring WeChat official accounts. It consists of a Python script (monitor.py) that interacts with a third-party API (down.mptext.top) to retrieve article metadata and a structured instruction set (SKILL.md) for the AI agent. The workflow includes a human-in-the-loop confirmation step before the agent modifies configurations, which mitigates the risk of unintended actions. No evidence of data exfiltration, malicious execution, or prompt injection was found; the code is transparent and strictly aligned with its stated purpose.