ClawHub
Back to skill

Security audit

Video Prompt Reverse Engineer

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only video prompt analysis skill with no evidence of hidden code execution, credential access, persistence, or unsafe data handling.

Safe to install from the reviewed artifacts. Only provide media you are comfortable having analyzed, and specify your desired output language if you do not want HappyHorse prompts written in Chinese.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill hard-codes a language requirement for HappyHorse prompts ('Write prompts in Chinese for best results') without asking for user preference or consent. This can override user intent, cause unexpected data transformation, and create prompt-generation behavior the user did not request, especially when the source material or downstream workflow is expected to remain in another language.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.