Help Center

Security checks across malware telemetry and agentic risk

Overview

This is a local help-center planning skill with disclosed memory files and no executable code or default data sharing.

Install if you want a local planning assistant for help-center strategy. Choose explicit activation if you do not want ordinary support-docs discussions to trigger it, and avoid putting secrets or sensitive customer data into ~/help-center/ planning files.

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

Medium

Confidence: 88% confidence
Finding: The activation rule includes broad topic phrases like help center, support docs, or ticket deflection, which can cause the skill to engage in ordinary conversations without a clear user request. This creates an over-broad trigger surface that may lead to unintended workflow activation, unnecessary data collection prompts, or context switching based on incidental mentions.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal