Back to skill

Security audit

Brand Guidelines

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward brand-guidelines helper that analyzes provided brand materials and applies style rules without hidden execution or persistence.

Installers should expect the skill to analyze brand evidence they provide, including documents or website material, to produce or apply a brand kit. Avoid supplying confidential brand assets unless you are comfortable having the agent inspect them for this purpose.

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.