ClawHub

WeChat Sender Windows

Security checks across malware telemetry and agentic risk

Overview

This skill openly automates a logged-in WeChat desktop app to send user-specified messages, including batches, but users should handle it carefully because it sends immediately.

Install only if you are comfortable letting a script control your logged-in WeChat window. Test with a harmless contact first, keep WeChat visible and focused, verify contact names and message text before running, and avoid bulk sending unless every recipient is intentional and consented.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This documentation describes automated control of the WeChat desktop client to search contacts and send messages, including bulk messaging, but it does not warn users about the risk of sending to the wrong recipient due to UI automation errors, stale focus, ambiguous contact names, or timing issues. In this context, omission of that warning is security-relevant because the skill operates a live messaging app and a mistake can immediately disclose sensitive or misleading content to unintended people at scale.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The script sends messages immediately after selecting a contact, with no confirmation step, preview, or dry-run mode. Because it uses UI automation and keystroke injection, any focus error, mistaken contact match, or malformed input can result in irreversible outbound messages being sent to the wrong recipient.

Missing User Warnings

High
Confidence
95% confidence
Finding
Batch mode repeats irreversible outbound actions across multiple recipients without any pre-send confirmation, recipient verification, rate limiting, or abort checkpoint. In this skill context, the danger is higher because GUI automation can misfire due to window focus changes or ambiguous search results, turning a single mistake into a mass-messaging incident or privacy breach.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal