ClawHub

Video Generation

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it uses TensorsLab to generate videos, may upload user-selected images, and saves generated video files locally.

Install only if you are comfortable sending prompts and any selected source images to TensorsLab, using a TensorsLab API key, and saving generated MP4 files locally. Prefer the environment variable over the --api-key flag to avoid exposing keys in shell history or process listings, and choose an output directory with enough disk space.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill explicitly instructs use of environment variables, shell commands, network API access, and local file writes, yet no declared permissions are provided. This creates a transparency and governance gap: users and platforms cannot accurately assess or constrain what the skill can do before execution.

Missing User Warnings

Low
Confidence
78% confidence
Finding
The skill states later that generated videos are saved under a local output directory, but it does not prominently warn users up front that running it writes files to disk. This can lead to unexpected filesystem changes, especially in constrained or sensitive working directories.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal