Ads Media Strategy

Security checks across malware telemetry and agentic risk

Overview

This is a plain advertising strategy planning skill with no code execution, credential access, account mutation, or persistence.

Safe to install as a planning aid. Review budget and bidding recommendations before acting, especially if it triggers during a general business discussion rather than a clearly advertising-focused request.

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
89% confidence
Finding
The trigger section includes very broad business terms like "growth," "revenue," "profit," and "campaign," which can match many unrelated requests and cause this skill to activate outside its intended scope. Over-broad invocation increases the chance that the agent applies specialized ad-planning behavior in the wrong context, leading to inappropriate recommendations, prompt-routing errors, or interference with safer/more relevant skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal