ClawHub
Back to skill

Security audit

youtube-summary

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed YouTube summarizer with expected external-service and cookie options, but users should be aware that full mode can send transcript or audio-derived content to OpenAI.

Install only if you are comfortable with a pinned third-party youtube2md npm dependency and with summaries potentially using OpenAI or a ChatGPT Codex session in full mode. For sensitive videos, use extract/simple mode or set YOUTUBE2MD_CAPTIONS_ONLY=1, and treat YouTube cookies and API keys as credentials.

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
93% confidence
Finding
The skill is configured to auto-activate whenever a message contains only YouTube URL(s), without requiring an explicit user intent phrase. This can cause the agent to invoke the skill on ambiguous inputs and potentially send transcript or audio-derived content to external services, creating unintended data processing and privacy exposure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.