ClawHub
Back to skill

Security audit

Ai Marketing Videos

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed inference.sh marketing-video helper, with normal external AI-service use but a risky CLI install command users should review first.

Install only if you are comfortable using inference.sh and its CLI login. Prefer manual download plus checksum verification instead of piping the installer directly to a shell, and do not submit secrets, unreleased campaign details, customer data, or regulated personal data unless your organization permits that third-party processing.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The examples instruct users to send prompts and later media/script content to external services via the inference.sh CLI, but they do not clearly warn that user-supplied text, scripts, audio URLs, and media references may leave the local environment and be processed by third-party systems. In this skill context, users may include unreleased product details, campaign plans, customer content, or proprietary assets, making silent external transmission a meaningful confidentiality and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.