Deep Ads Research

Security checks across malware telemetry and agentic risk

Overview

This is a text-only advertising research planning skill; its trigger wording is broad, but it does not request account access, credentials, code execution, persistence, or data export.

Use this skill for deep advertising research where you can provide a research question, hypotheses, and a decision deadline. Treat its budget or strategy recommendations as planning input and review them before changing spend or campaign 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
93% confidence
Finding
The trigger section is broad enough to match many ordinary marketing and business questions, which can cause the orchestrator to activate outside its intended niche. Over-broad invocation is dangerous because it can route users into a specialized planning flow that produces high-confidence ad strategy recommendations without sufficient scoping, increasing the chance of irrelevant, misleading, or unsafe business guidance at scale.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal