Security audit
omnihuman
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent RunAPI helper for OmniHuman video tasks, with disclosed API-key use, media upload, and paid-task safeguards.
Before installing, understand that using this skill can upload local image/audio media to RunAPI and may create paid OmniHuman tasks. Use a scoped RunAPI API key, review request.json before submission, and only use browser login or background execution when you explicitly want that behavior.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.