ClawHub

Skill Veo3 Video Gen

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it generates videos through Google Gemini/Veo, with normal cautions around API keys, local file paths, and third-party data submission.

Install this only if you intend to send generation prompts and any selected reference or last-frame images to Google Gemini/Veo. Use a scoped Gemini API key through the environment, avoid passing secrets on the command line, do not submit confidential or regulated media, and review --filename paths before running so the script writes only where you expect.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
92% confidence
Finding
The skill documentation describes capabilities to read environment variables, perform network requests to an external API, write files, and invoke shell tools like ffmpeg, but it does not declare permissions or boundaries for those actions. That creates a real security governance gap: users and enforcement layers cannot easily determine that prompts, API keys, and generated media may be transmitted externally and that local files/shell execution are involved.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The documentation tells users where the API key is stored and instructs them to send prompts to Google Gemini, but it does not clearly warn that prompts, reference images, and possibly derived media are transmitted to a third-party service. In this context, users may unknowingly submit sensitive creative briefs, product assets, or private images to an external provider.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal