ClawHub

Text To Video Explanation Ai

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it advertises: use NemoVideo cloud APIs to turn scripts or uploaded documents into explainer videos.

Install only if you are comfortable sending scripts, prompts, and uploaded files to NemoVideo cloud services. Avoid confidential, regulated, or proprietary material unless you have reviewed the service's privacy and retention terms, and use a dedicated revocable NEMO_TOKEN when possible.

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

High
Confidence
96% confidence
Finding
The routing table sends "Everything else" to the SSE action, which effectively makes this skill a catch-all for many unrelated prompts. In a multi-skill environment, that can cause unintended activation and silent forwarding of user prompts to the external Nemo API, creating prompt hijacking and data exfiltration risk beyond the user’s reasonable expectations.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description is broad marketing copy about converting written scripts into videos and lacks precise invocation boundaries. That ambiguity increases the chance the platform routes generic content-creation requests here, which may lead to unintended external processing of user data and confusion about what the skill will do.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill processes user scripts, prompts, and uploaded files through external cloud endpoints, but the description does not clearly warn users that their content will be transmitted off-platform. Because supported inputs include TXT, DOCX, PDF, and SRT up to 200MB, users may upload sensitive business or educational materials without informed consent, increasing privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal