ClawHub
Back to skill

Security audit

Claude Usage Tracker

Security checks for vulnerabilities and agentic risk

Overview

The skill is a personal Claude.ai usage tracker, but it depends on a missing local script that would handle sensitive account and billing data outside the reviewed package.

Review this before installing because it appears incomplete: the important Python script is not in the package, yet the skill tells the agent to run it. Only use it if you know exactly which local script will be executed and are comfortable storing Claude.ai usage, spend, and balance data in the disclosed memory file.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation criteria are broad enough to trigger on general billing, credit, and usage questions, which can cause the agent to invoke a network-enabled scraping skill outside a narrowly intended Claude.ai dashboard context. While this is not directly code-execution or data-exfiltration logic, it increases the chance of unnecessary access to account-usage data and can expand the skill’s operational scope beyond least-privilege expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.