Brand Voice Profile

• Outcome: Pass
• Latest audit: May 28, 2026 at 6:09 AM UTC
• Version:
  1.0.0

Overview

This skill appears to help create local brand-voice profiles, with privacy and input-scoping cautions but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you are comfortable with the agent storing brand voice data on disk. Use it with writing samples, posts, or URLs you are authorized to analyze, avoid sensitive client material unless needed, and use simple profile names without path characters.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Confidence: 89% confidence
• Finding: The skill instructs the agent to create and maintain `brand-voice/profile.json`, which stores potentially sensitive user-authored preferences, examples, and writing patterns, but it does not tell the user that this information will be persisted locally. While this is not overtly malicious, undisclosed storage can create privacy and data-handling risks, especially if authentic writing samples or client-specific voice profiles are later reused, exposed, or synced by other tools.

VirusTotal

65/65 vendors flagged this skill as clean.