YouTube Analysis

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward YouTube transcript analysis helper with disclosed external fetching and no evidence of hidden data access or persistence.

Install this if you are comfortable with the agent fetching YouTube transcript data when you ask it to analyze a video. Be aware that the README describes automatic activation on YouTube URLs, so if you only mention a link incidentally, you may want to clarify whether you want transcript extraction and analysis.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The README states that the skill activates automatically whenever a user provides a YouTube URL, which is an overly broad trigger condition. Broad auto-activation can cause the agent to invoke the skill in unintended contexts, increasing the chance of processing untrusted content, wasting resources, or interfering with user intent when a URL is mentioned incidentally rather than as an explicit request for analysis.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal