ClawHub
Back to skill

Security audit

Wechat

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill for summarizing public WeChat pages, with no code execution, credentials, persistence, or account actions requested.

Install this only if you want help summarizing public WeChat links. Do not provide private chats, credentials, login-only pages, or ask it to send messages or manage account actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description says the skill should be invoked whenever access or automation of WeChat-related content is needed, which is overly broad and can cause the agent to route many loosely related requests into this skill. In an ecosystem where skills may browse external pages, broad triggering increases the chance of unnecessary web access, unintended data handling, and misuse outside the stated boundary of only public pages.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.