ClawHub
Back to skill

Security audit

Weixin

Security checks across malware telemetry and agentic risk

Overview

This is a coherent WeChat Official Account API helper, but it handles powerful account credentials and should be used carefully.

Install only if you intend to let the agent operate a WeChat Official Account or miniprogram API. Treat WX_SECRET and any printed access_token as secrets, avoid logging command output, and require explicit confirmation before publishing content, sending templates, or using the generic call command for write actions.

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 describes executable CLI behavior that uses environment variables for secrets, performs network requests to external WeChat APIs, and writes a local token cache file, but it declares no permissions. That mismatch is a real security issue because users and hosting agents are not given an explicit trust boundary for secret access, outbound communication, or filesystem writes, which can lead to unintended secret exposure, unauthorized API actions, or policy bypass in permission-gated environments.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The token subcommand prints the WeChat access_token directly to stdout, which can expose credential material to shell history capture, terminal logging, CI logs, or other process wrappers. In a CLI explicitly designed for API operations, this is more dangerous because users are likely to pipe, script, or record command output during automation and troubleshooting.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.