ClawHub
Back to skill

Security audit

Qclaw Speaker

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed text-to-speech skill with expected installer, model download, audio generation, and optional online speech behavior.

Install only if you are comfortable with Python package installation and model downloads. Use sherpa or Windows SAPI for offline speech; using Edge TTS may send the text being spoken to Microsoft’s online service. In sensitive environments, prefer pinned dependencies and verified model archives before running the installer.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation advertises executable capabilities including shell commands, file reads/writes, and network access, but the skill declares no permissions. This creates a real security gap because users and the host platform are not given an explicit trust boundary for actions like installing packages, downloading models, modifying config.json, or making online TTS requests to Microsoft services.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.