Youtube Comment Manager

Security checks across malware telemetry and agentic risk

Overview

This skill clearly describes a YouTube comment-management integration, including posting, deletion, moderation, and bans, and those capabilities fit its stated purpose.

Install only if you are comfortable giving AgentPMT-hosted tooling access to manage YouTube comments through your connected Google account. Use human review before deleting comments, rejecting comments in bulk, posting replies, or banning authors, especially because bans must be reversed through YouTube Studio.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill exposes destructive actions like delete_comment, moderate_comments with rejected status, and irreversible author bans, but it does not recommend confirmation or warn agents to seek explicit user approval before taking high-impact moderation actions. In an autonomous or semi-autonomous agent setting, this increases the risk of accidental deletions, wrongful bans, and irreversible moderation mistakes affecting channel operations and user trust.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal