ClawHub
Back to skill

Security audit

Video Script Gen

Security checks across malware telemetry and agentic risk

Overview

This is a simple, non-executable video-script writing skill with a noticeable off-platform paid upsell that users should verify separately.

Use the script-writing guidance normally, but do not treat the Telegram Pro offer, external files, or advertised Python scripts as reviewed by ClawHub. Verify the seller before paying, and inspect any separately delivered files before running them.

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
88% confidence
Finding
The skill defines broad content-generation capabilities but does not specify clear activation boundaries, allowed topics, or constraints. In an agent environment, this ambiguity can cause the skill to be invoked for risky requests such as deceptive marketing, health-related promotion, or other sensitive persuasive content without appropriate guardrails.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.