ClawHub
Back to skill

Security audit

AI Video Scene Director

Security checks across malware telemetry and agentic risk

Overview

This skill is a planning-only AI video prompt workflow with no executable code or hidden data access.

Reasonable to install for AI video planning. Expect it to produce structured creative briefs and prompts, not media or code. The declared Python requirement is a minor metadata oddity because the inspected package is markdown-only.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is broad enough to trigger on many general creative or video-related requests, which can cause the agent to invoke this skill in situations where it is not the best match. Over-broad activation increases the chance of prompt-scope hijacking, irrelevant tool use, or accidental steering of user requests into this workflow without clear user intent.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.