Brand

Security checks across malware telemetry and agentic risk

Overview

This is a text-only branding assistant with broad activation wording but no code, credentials, persistence, or hidden actions.

Install if you want a broad branding and positioning assistant. Be aware it may activate for general business-branding prompts, and independently verify trademark, domain, legal, and competitive research before relying on naming or launch decisions.

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)

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger description is extremely broad and includes generic branding- and business-related phrases, which can cause the skill to activate in many loosely related contexts. Overbroad activation can lead to incorrect tool/skill selection, unintended disclosure of user context to the skill, and unreliable behavior across unrelated tasks, even though the file does not contain direct code execution or data exfiltration logic.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal