AI Video Director

Security checks across malware telemetry and agentic risk

Overview

This appears to be a video-prompt/storyboard helper with minor routing and language-selection concerns, not a harmful or privileged skill.

Install if you want help drafting AI video prompts or storyboards. Be explicit about the target platform and output language, and review generated prompts before using them in paid or public video-generation tools.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list is broad enough to match many ordinary video-related requests, which can cause the skill to activate outside the user's explicit intent. In an agent ecosystem, overbroad activation can hijack routing, suppress more appropriate skills, or inject unintended guidance into generic conversations about video creation.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The skill states language preferences for prompts without requiring explicit user choice, which can override user expectations or produce outputs in an unintended language. While not directly enabling code execution or data exfiltration, it can degrade reliability, cause confusing behavior, and create prompt-routing side effects in multilingual contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal