Deep Ads Analyst

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:13 PM UTC
• Version:
  1.0.0

Overview

This is a prompt-only advertising analysis skill with no code, credentials, persistence, or account-changing behavior.

Safe to install as an advisory marketing-analysis skill. Review recommendations that affect ad spend, billing, tracking, or account configuration before acting, and require explicit approval before connecting any future tools with access to advertising accounts.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger terms are broad business and marketing words like 'growth,' 'revenue,' 'profit,' and 'campaign,' which can cause the skill to activate for many unrelated requests. Over-broad activation is a real security and reliability issue because it increases the chance the agent applies domain-specific instructions in the wrong context, leading to misrouting, unintended data handling, or inappropriate strategic guidance.

VirusTotal

65/65 vendors flagged this skill as clean.