Ads Incident Tickets

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only ad-operations ticketing skill with no code execution or hidden access, though its trigger wording is broader than ideal.

Safe to install for drafting ad-operations incident tickets. Use it for actual ad incidents or account-health triage, not general growth strategy, and share only the account IDs, logs, thresholds, and owner contacts needed for the specific issue. Manually review any recommended pause, rollback, spend, billing, or platform-setting action before applying it.

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
92% confidence
Finding
The trigger conditions are broad enough to match many ordinary advertising, growth, and revenue-related requests, which can cause this specialized incident-routing skill to activate outside its intended scope. Unintended invocation can steer users into incident-ticket workflows, produce irrelevant operational guidance, and increase the chance that other guardrails or more appropriate skills are bypassed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal