YouTube API CLI

Security checks across malware telemetry and agentic risk

Overview

This YouTube CLI skill is coherent and not malicious, but it should be reviewed because it gives an agent live authority to publish or change YouTube account content without clear safety boundaries.

Install only if you trust the referenced GitHub CLI and are comfortable granting it YouTube account access. Pin and verify the installed version where possible, use a dedicated Google OAuth client with minimal scopes, protect or revoke tokens when no longer needed, and require explicit approval before uploads, channel updates, playlist edits, thumbnail changes, or other account-mutating commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents destructive or account-modifying operations such as uploads, playlist insertion, and channel updates without an explicit warning that these actions affect live YouTube resources. In an agent or automation context, this increases the risk of unintended public uploads, metadata changes, or playlist modifications being executed against a real user account.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal