YouTube Shorts Automation

• Outcome: Review
• Latest audit: May 28, 2026, 1:04 PM
• Version:
  1.0.0

Overview

This skill fits its YouTube Shorts automation purpose, but it needs Review because it can publish videos publicly even when the user selects a non-public privacy option.

Install only if you are comfortable reviewing or fixing the upload script first. Protect client_secret.json and token.json, avoid enabling cron until the privacy bug is fixed, and test with a dedicated YouTube channel before allowing automated uploads.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

• Confidence: 97% confidence
• Finding: The CLI exposes a --privacy option, but the value is ignored because upload_video() hardcodes privacyStatus to public. In an automation pipeline, this can cause unintended public publication of videos the operator expected to keep private or unlisted, leading to accidental disclosure and operational or reputational harm.

Vague Triggers

Medium

• Confidence: 80% confidence
• Finding: The invocation text is broad enough to match general short-form video creation or upload tasks, which may cause the skill to activate in contexts beyond the user's intended workflow. Because this skill includes automated publishing behavior, over-broad triggering increases the risk of unintended external actions such as content generation or upload without sufficiently specific user intent.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill advertises automatic YouTube uploads and daily cron execution but does not present an explicit warning that it can autonomously publish content to a public platform. In this context, missing user-facing notice is dangerous because accidental invocation or misunderstanding could lead to unauthorized posting, reputational harm, or policy violations on the linked YouTube account.

Missing User Warnings

Low

• Confidence: 84% confidence
• Finding: The setup references OAuth client secrets and persistent tokens without warning users that these files are sensitive credentials that can enable account access if exposed. In a workflow that also includes automation and cron execution, poor credential handling raises the risk of token leakage, unauthorized uploads, or long-lived account compromise.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The document instructs users to create OAuth client credentials and notes that a persistent `token.json` will be generated, but it does not warn that these files contain sensitive authentication material tied to a Google account and channel. In an automation skill that runs on cron and uploads content, local credential persistence increases the risk of accidental exposure, reuse by other local processes, or inclusion in backups/repositories.

VirusTotal

65/65 vendors flagged this skill as clean.