Brandkit
Security checks across malware telemetry and agentic risk
Overview
This is a design-only prompt skill for generating brand-kit images, with no executable code or hidden data access in the artifacts.
Installers should treat this as a creative image-generation helper. It does not appear to need elevated permissions or local data access, but users should still review generated logos and reference-inspired outputs for originality, trademark risk, and fit before using them commercially.
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
41/41 vendors flagged this skill as clean.
