ClawHub
Back to skill

Security audit

Youtube Watcher 1.0.0

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward YouTube transcript helper, with some caution needed because its trigger phrases are broader than its actual YouTube-only workflow.

Install this if you want an agent to fetch YouTube captions using Python and yt-dlp. Use it only with explicit YouTube URLs or clear YouTube transcript requests, and be aware that it will contact YouTube or other yt-dlp-supported endpoints if given such input.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes a local Python script and an external binary (`yt-dlp`), which gives it shell execution and file-read capabilities, yet it declares no explicit permissions or guardrails. This is dangerous because ambiguous or undeclared capabilities reduce policy enforcement and user visibility, increasing the chance the skill is invoked in contexts where code execution or local file access was not expected.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrase `analyze video` is overly broad and can match generic user requests unrelated to YouTube transcripts. This is dangerous because it may cause unintended activation of a skill that executes commands and fetches remote content, creating unnecessary exposure and surprising behavior.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description and trigger set do not clearly define the boundaries of activation, so the skill may be selected for general video-analysis requests beyond its actual function of fetching YouTube subtitles. In context, this is more dangerous because the skill performs shell-backed operations against remote URLs, so ambiguous routing can expand execution of higher-risk behavior to unintended prompts.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.