ClawHub
Back to skill

Security audit

YouTube Shorts 자동 생성

Security checks across malware telemetry and agentic risk

Overview

This skill matches its stated YouTube Shorts automation purpose, but it asks the agent to download and run mutable external code and can upload to YouTube with under-declared credentials and controls.

Install only if you are comfortable auditing and running the linked GitHub repository. Review scripts/setup.sh, requirements.txt, the YouTube uploader, and credential storage before providing GEMINI_API_KEY or Google OAuth files. Run it in an isolated workspace or VM first, keep uploads private by default, and require a manual confirmation before any paid generation or YouTube upload.

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
92% confidence
Finding
The trigger phrases are generic enough to match ordinary user requests such as asking to create a Shorts video or collect trends, which can cause the skill to activate when the user did not intend to invoke this specific automation. In this skill, unintended activation is more dangerous because the documented workflow can lead to paid API usage and downstream publishing actions, increasing the consequence of accidental execution.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises automatic YouTube upload in its description but does not prominently warn that it may perform account-affecting external actions. This is risky because a user may invoke the skill for content generation without realizing it can publish to YouTube or consume paid services, leading to unintended uploads, reputation impact, or account changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.