ClawHub
Back to skill

Security audit

Youtube Podcast summarizer via Elevenlabs

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent YouTube-to-audio summarizer that uses disclosed external services and a local backend, with privacy and cost considerations users should understand.

Before installing, review the external GitHub backend and npm dependencies, protect the required API keys, set spending limits where possible, and avoid submitting private, confidential, or regulated videos unless you accept processing by Supadata, OpenRouter/Cerebras, and ElevenLabs.

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
96% confidence
Finding
The skill explicitly routes user-supplied YouTube URLs and derived transcript content through multiple third-party services (Supadata, OpenRouter/Cerebras, and ElevenLabs) but does not warn users about that data sharing at the point of use. This creates a real privacy and transparency issue because users may submit private, sensitive, or regulated content without understanding it will be transmitted to external processors.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.