Token Usage Tracker

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  1.0.0

Overview

This is a local token-usage tracking skill with disclosed tracking behavior and no evidence of exfiltration, credential access, or unsafe automation.

Safe to install from the reviewed evidence. Use explicit token-usage wording when you want it to run, and be aware it may keep local usage totals/history in .usage-tracker.json unless configured otherwise.

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 (2)

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrases include broad, natural-language expressions such as “消耗了多少” and “花了我多少token,” which could match ordinary conversation and cause the skill to activate unexpectedly. In a tracking skill, overbroad activation can lead to unintended interception of user requests, confusion about assistant behavior, and unnecessary exposure of conversation metadata or usage history.

Natural-Language Policy Violations

Medium

• Confidence: 80% confidence
• Finding: The skill metadata and trigger design are written only in Chinese and imply Chinese-language behavior without any user-language negotiation or opt-in. This can cause the skill to activate or respond in a language the user did not request, degrading usability and potentially obscuring what data is being tracked or reported.

VirusTotal

67/67 vendors flagged this skill as clean.