Ads ROAS Forecast

Security checks across malware telemetry and agentic risk

Overview

This is a plain prompt skill for advertising ROAS forecasting, with no hidden execution or data-access behavior found.

Install this if you want help modeling ad-platform ROAS, attribution windows, and budget scenarios. Use real baseline metrics and review assumptions before acting on spend recommendations, especially because the broad trigger wording may make the skill appear in some general marketing conversations.

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 activate on many generic business or marketing prompts, not just specialized ROAS forecasting tasks. This can cause inappropriate skill routing, where the agent applies ad-budgeting guidance in contexts lacking the required inputs or safeguards, increasing the chance of misleading recommendations or overconfident financial advice.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal