ClawHub
Back to skill

Security audit

How Much Claude Left?

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently checks Claude subscription quota using the local Claude CLI, with the main cautions being automatic CLI automation and a scoped trust-prompt response.

Install only if you are comfortable with a skill launching tmux and Claude Code CLI locally, using your existing Claude login to run /usage, and automatically trusting a temporary scratch folder. Review the shell script first if you require manual control over Claude CLI trust prompts.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description includes very broad trigger phrases like general rate-limit, slowness, and usage questions, which can cause the skill to auto-activate in routine support contexts beyond explicit user intent. That increases the chance an agent will run local automation unexpectedly, including launching tmux and Claude CLI, which is risky because the skill performs actions rather than merely providing advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states it automatically handles the Claude Code CLI 'trust this folder' prompt but does not prominently warn the user that it is programmatically accepting a trust decision on their behalf. Automatically bypassing or answering trust prompts weakens an important safety boundary, because trust prompts exist to prevent unreviewed directories from being granted elevated access or treated as safe.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.