generate-personal-brand-ad-creative-brief

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  1.0.0

Overview

This is a low-risk instruction-only skill for drafting personal-brand ad creative briefs, with no code, credentials, persistence, or hidden install behavior.

Reasonable to install for drafting ad creative briefs. Review generated copy and images before publishing, especially for brand claims, copyright, privacy, and platform ad-policy compliance. In tightly controlled workspaces, limit which enrichment capabilities the agent may use.

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: 88% confidence
• Finding: The suggested invocation phrase is generic enough that ordinary user requests could unintentionally trigger this skill when the user did not explicitly intend to invoke it. In an agent environment, broad trigger phrases can cause misrouting, unexpected tool use, or generation of ad-planning content in contexts where a normal conversational response was expected.

VirusTotal

65/65 vendors flagged this skill as clean.