Back to skill

Security audit

avatar-single-scene

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly scoped avatar-video workflow that uses disclosed Pruna API calls after user approval.

Before installing, make sure you are comfortable sending approved portraits, scripts, and optional audio to Pruna and using a PRUNA_API_KEY for potentially paid generation. Review generated scripts before running them, and keep the manifest out of places where prompt text, media URLs, or prediction IDs should not be stored.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.