Ads Human Handoff

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only advertising support skill that prepares troubleshooting advice and escalation packets without code, credential use, persistence, or account-changing authority.

Install this if you want an ads-focused assistant that can give troubleshooting steps and prepare escalation handoff details. Review any budget, pause, cap, policy, or campaign recommendations before applying them in an ad platform, and avoid sharing sensitive business data that is not needed for the issue.

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 trigger conditions are broad enough to activate on general advertising, growth, and business-performance discussions, not just explicit human handoff requests. This can cause the skill to intercept conversations outside its intended scope and steer users toward escalation workflows or specialized ad-ops guidance when a different skill or safer generic handling would be more appropriate.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal