Skill usage tracker

• Outcome: Pass
• Latest audit: May 28, 2026, 10:17 AM
• Version:
  1.0.0

Overview

This is a simple local audit skill that discloses rule checking and violation logging, with no evidence of hidden network access, destructive behavior, or credential use.

Before installing, treat this as a local monitoring tool: confirm what gets written to skill_violations.log and daily reports, avoid using it where sensitive conversations could be logged without consent, and periodically delete or rotate logs if they are no longer needed.

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

Medium

• Confidence: 88% confidence
• Finding: The skill states that violations are recorded to a local log file, but the description does not clearly warn users that their interactions may be logged. Undisclosed logging creates a privacy and transparency problem, especially if prompts or outputs can contain sensitive or personal data.

VirusTotal

66/66 vendors flagged this skill as clean.