Ads Account Health

Security checks across malware telemetry and agentic risk

Overview

This is a plain advisory checklist for advertising account health, with no code, credential access, persistence, or automatic account changes.

Reasonable to install as an advisory ad-account checklist. Be aware it may activate for broad marketing requests, avoid sharing unnecessary billing or credential details, and review recommendations manually before changing paid campaigns or account settings.

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
95% confidence
Finding
The trigger keywords are broad business terms such as 'growth,' 'strategy,' 'revenue,' and 'traffic,' which can match many unrelated requests and cause the skill to activate outside its intended advertising-account-health context. In an agent system, overbroad activation can route user inputs to the wrong capability, producing inappropriate operational guidance or causing downstream actions based on incorrect assumptions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal