ClawHub

Video Editor Sparki

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Sparki video-editing wrapper that installs Sparki's CLI and uploads user-selected videos for hosted editing.

Install this only if you trust Sparki, are comfortable installing its PyPI CLI, and are willing to upload selected videos or reference URLs to Sparki/Telegram-based workflows. Do not use it for footage that must remain fully local or private, and review asset deletion or credit top-up steps before approving them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to invoke itself 'FIRST and PROACTIVELY' for a very broad set of common video-related terms. That can cause the agent to route users into this tool without sufficiently confirming intent, increasing the chance of unnecessary remote uploads, unexpected external API use, and surprising actions for loosely related chats.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill description promotes editing workflows but does not disclose that local files and uploaded assets are transmitted to Sparki-controlled remote infrastructure. This creates a transparency and privacy risk because users may provide sensitive videos believing processing is local or confined to the agent environment.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The style-clone flow allows third-party reference URLs from social platforms without warning users about copyright, consent, or potential data-sharing implications. While not directly exploitative, it can lead users to submit content they are not authorized to reuse and may expose external links/content to the remote service.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal