Global Ads Helper

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent global ads planning helper with no executable code or hidden access, though its broad trigger words may cause occasional unintended activation.

Install this if you want structured help planning international paid media budgets and expansion. Invoke it with specific prompts about multi-country ads, budget allocation, or expansion ROI, and review any forecasts before using them for real spending 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

Medium
Confidence
90% confidence
Finding
The trigger keywords are broad generic marketing terms like 'market', 'strategy', 'revenue', and 'scale', which can cause the skill to activate for many unrelated requests. Over-broad invocation boundaries increase the chance of unintended routing, causing the agent to apply this skill in contexts where its assumptions or outputs are inappropriate and may mislead downstream decisions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal