ClawHub
Back to skill

Security audit

HeyGen AI Avatar Video (Lite)

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only HeyGen API guide with expected third-party API use and no hidden execution behavior.

Before using it, protect your HeyGen API key, expect that generated videos may consume paid credits, avoid submitting sensitive or non-consensual voice/avatar material, and review the HeyGen terms and the disclosed affiliate/premium links before paying.

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)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs users to make authenticated API calls that can incur charges and may process sensitive text, voice, or avatar data, but it does not clearly warn about billing implications, data handling/privacy considerations, or the risks of submitting personal or cloned-voice content to a third-party service. In this context, the omission is security-relevant because users may unknowingly expose personal data or trigger paid usage through copied commands that appear frictionless and safe.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.