ClawHub

Free Video Generator Like Sora

Security checks across malware telemetry and agentic risk

Overview

This video-generation skill is coherent, but it can broadly route ordinary text and uploaded media to a third-party cloud service without clear upfront disclosure.

Review before installing. Use this only when you are comfortable sending prompts, uploaded media, and related session data to the NemoVideo backend. Avoid private or confidential media, and use explicit video-generation commands to reduce accidental activation.

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
76% confidence
Finding
The invocation guidance is broad enough that ordinary phrases like sharing prompts or vague creative requests could activate the skill unintentionally. That can cause users to send prompts or media to a remote service without clear intent, increasing privacy and surprise-execution risk.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The catch-all rule routing 'everything else' to SSE makes activation scope overly permissive. In practice, ambiguous user text could trigger remote processing, session use, or data transmission even when the user did not explicitly request this skill's functionality.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to connect to a third-party backend, acquire tokens, create sessions, and potentially upload user prompts and media, yet explicitly says to keep technical details out of chat. That omission deprives users of informed consent about remote transmission and handling of potentially sensitive content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal