ClawHub

Wecom Voice

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims, but it can send real WeCom voice messages and builds local PowerShell and shell commands from user-provided text without clear safeguards.

Review this before installing if you may dictate sensitive text or rely on agents to choose recipients. Use it only with trusted, controlled inputs, confirm the recipient explicitly, and prefer a version that escapes PowerShell content, uses argument-array process execution, removes the default recipient, and cleans up generated media files after sending.

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documentation indicates it writes generated voice media into the user's WeCom/OpenClaw media flow and then sends it, but it does not clearly warn the user that local files will be created in `~/.openclaw/media/inbound` and used for message delivery. This can mislead users about persistence, message routing, and side effects, increasing the chance of unintended disclosure or accidental sending of synthesized content.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill hardcodes a Chinese TTS voice (`Microsoft Huihui`) without presenting user choice or opt-in, which can cause unintended language output, miscommunication, or privacy-sensitive content being spoken in an unexpected voice/language. In a messaging context, this reduces user control over what is sent and may produce incorrect or embarrassing voice messages.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal