ClawHub
Back to skill

Security audit

CreateVideo Podcast to Video

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward video-making helper, with disclosed local media processing and optional text-to-speech through an external ListenHub MCP server.

Install this only if you are comfortable using ffmpeg locally and, for text-to-speech, running the ListenHub MCP server. Consider pinning or reviewing the npm package before use, and avoid sending confidential scripts or sensitive personal/business content to the TTS service unless you trust that provider.

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
92% confidence
Finding
The skill declares a very broad trigger surface for requests like '创建视频' or generic requests to make a video, which can cause unintended activation on ambiguous user input. In an agent setting, overbroad activation can route unrelated content into file creation, TTS generation, and media-processing workflows without clear user intent, increasing the risk of unauthorized processing or accidental tool use.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.