ClawHub
Back to skill

Security audit

Youtube Watcher

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: fetch and cache YouTube transcripts and thumbnails, with disclosed local tooling and optional cookie-based fallback.

Before installing, be aware it can run local CLI tooling, make requests to YouTube, save transcript/cache files locally, and optionally use browser cookies through yt-dlp for blocked or restricted videos. Only enable browser-cookie fallback for accounts and videos you are comfortable exposing to that local tool.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes a local Python script and an external binary (`yt-dlp`) through shell commands, but declares no permissions for shell execution or file access. This creates a transparency and governance gap: a host agent may permit execution without surfacing the real capabilities to users or policy controls, increasing the chance of unintended command execution against user-supplied URLs.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger phrases are broad enough to match many ordinary requests about videos, which can cause the skill to activate unexpectedly. In this skill's context, unexpected activation is meaningful because the skill leads to shell execution and network-backed transcript fetching, so overbroad routing can expand the attack surface and cause unnecessary external calls.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.