Ai Traffic Tracking

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only guide for tracking AI referral traffic in GA4/GSC and does not install code or access data on its own.

Safe to install as a reference guide. Before applying its GA4 regex, custom channel group, custom report, or GTM suggestions, review them against your analytics setup and keep a copy of existing reporting settings because those manual changes can affect traffic categorization.

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
91% confidence
Finding
The skill description uses expansive trigger language such as 'also use when the user mentions' followed by many broad phrases, which can cause the skill to activate outside narrow user intent. Over-broad invocation can route unrelated conversations into this skill, leading to incorrect guidance, context leakage across skills, or suppression of better-matched controls and workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal