ClawHub
Back to skill

Security audit

video-transcript

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward video-subtitle extractor with expected local file storage and no evidence of hidden or harmful behavior.

Install yt-dlp only from a trusted source, use the skill only for video links you intend to process, and delete the local video-transcripts folder if the subtitles contain sensitive content. Do not rely on it for Chinese translation unless a separate translation step is added.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill advertises shell, file read, and file write capable behavior via yt-dlp usage but does not declare any permissions. Undeclared execution and filesystem capabilities reduce transparency and can bypass policy or user expectations, increasing the risk of unsafe command execution, unintended file access, or unsafe artifact handling if the skill is later implemented or invoked automatically.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.