ClawHub
Back to skill

Security audit

WeChat MP Monitor

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WeChat article monitor that stores local watch/history data and can send Feishu/Lark notifications, with no evidence of hidden or destructive behavior.

Install only if you are comfortable with the skill fetching article URLs you provide, saving watchlist/history under ~/.wechat_mp_monitor, and sending notification content to Feishu/Lark when configured. Prefer FEISHU_WEBHOOK over saving webhook URLs in the watchlist, treat webhook URLs as secrets, and remove the cron entry and local data directory when you no longer need monitoring.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation describes operations that require network access, environment-variable use, and persistent local file reads/writes, but it does not declare permissions for those capabilities. This creates a transparency and consent problem: users or hosting platforms may invoke the skill without realizing it can access webhook secrets, write data into the home directory, and make outbound requests.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script stores Feishu webhook URLs in the watchlist JSON under the user's home directory without any warning, minimization, or permission hardening. Webhook URLs are bearer-style secrets in many chat systems, so local disclosure can let another local user or process send spoofed notifications into the connected Feishu channel.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.