ClawHub
Back to skill

Security audit

WeChat MiniProgram CloudBase Deploy

Security checks across malware telemetry and agentic risk

Overview

The skill matches its deployment purpose, but needs review because it recommends disabling WeChat's upload IP whitelist while using private-key-based upload authority.

Install only if you are comfortable letting the agent help deploy CloudBase functions and upload a WeChat Mini Program using a local private key path. Keep the upload key local, prefer a stable IPv4 egress or controlled CI runner over disabling the upload IP whitelist, and treat whitelist disabling as a temporary last resort with key rotation afterward.

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
93% confidence
Finding
The skill instructs the agent to run shell commands and use environment-driven tooling (`npm install`, `tcb`, `node` upload scripts) but does not declare any permissions or constraints for those capabilities. In an agent setting, undeclared shell/env access weakens security review and can enable command execution or secret exposure without clear user visibility.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The document recommends turning off the mini-program upload IP whitelist as the preferred fix for IPv6 upload failures, while downplaying the security tradeoff. Disabling a network access control weakens defense-in-depth and makes code upload possible from any source that has the private key, increasing exposure if the key is mishandled or a build host is compromised.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.