ClawHub

Youtube Data CLI

Security checks across malware telemetry and agentic risk

Overview

This YouTube management skill is coherent and not malicious, but it needs review because it can make live account changes using broad OAuth access without clear confirmation safeguards.

Install only if you intend to let an agent manage a YouTube account. Prefer read-only API-key use for public searches, verify and pin the npm package before global installation, protect OAuth refresh tokens, use the narrowest scopes that work, and require explicit confirmation before any upload, update, delete, comment, rating, subscription, abuse report, moderation, or channel-branding change.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger list includes generic phrases like "YouTube", "subtitles", and "like video", which can cause the skill to activate for broad everyday requests beyond a narrowly intended scope. Because this skill supports write and destructive actions, over-broad invocation increases the chance the agent routes a user into powerful account-modifying workflows without sufficient intent verification.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This section documents destructive and account-modifying operations such as delete, update, rating, moderation, and uploads without any warning, dry-run guidance, or confirmation requirement. In an agent setting, that omission is dangerous because users may not realize these commands can change live YouTube account state, enabling accidental or prompt-induced harmful actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal