Tongyong Shenhe

通用内容审核 Skill。配置驱动，适用于所有 d.php 后台站点。内置审核规则自动判断 + 可选技术部API增强。其他组只需填写站点账号密码即可使用，审核规则可自行修改适配。

Before installing or running this skill, consider the following: 1) The script requires admin credentials and the TOTP seed — giving the seed grants long-term 2FA capability, so avoid supplying it unless you trust the operator; prefer a service account with limited permissions or use manual/interactive TOTP entry. 2) The skill uses system curl and expects a VPN interface (ppp0); the registry metadata did not declare curl — verify your environment and run in an isolated/test account first. 3) The moderation API is optional but accepts an arbitrary api_url and api_key; double-check the URL (the example domain looks unfamiliar). If you configure an external API, you will be sending full item text and metadata offsite — only enable this for trusted internal endpoints. 4) The docs explicitly suggest sending rules.json (and possibly example content) to external AI services (e.g., Claude) — this can leak policy or sample content; avoid sending sensitive examples. 5) Run the tool in --dry-run mode first; audit review.py yourself (search for unexpected network endpoints or hidden behavior), and consider executing it from a network-isolated environment or with network controls to prevent unintended exfiltration. If you want, I can list exact lines in review.py to inspect and suggest safer configuration alternatives (e.g., avoid storing TOTP seed, restrict api_url to internal hostnames).

Type: OpenClaw Skill Name: tongyong-shenhe Version: 1.0.0 The skill is designed to automate content moderation on 'd.php' framework sites but exhibits several high-risk behaviors. It requires sensitive administrative credentials, including a TOTP seed (Base32 secret), and uses subprocess to execute system 'curl' commands for network requests. Most notably, it optionally exfiltrates content to an external API hosted on a suspicious, non-corporate domain (zyaokkmo.cc) for 'AI enhancement.' While the logic aligns with the stated purpose of moderation, the combination of credential handling, shell execution, and data transmission to an untrusted endpoint presents a significant security risk.