ClawHub
Back to skill

Security audit

Claude Usage Release

Security checks for vulnerabilities and agentic risk

Overview

This skill only automates Claude Code's usage screen and reports local quota information, with no evidence of hidden persistence, exfiltration, or account-changing behavior.

Install this only if you are comfortable letting the agent open your authenticated Claude Code CLI and read Claude usage information, including limited local cached token counts if the expect-based flow is unavailable. It does not appear to modify billing, enable extra usage, or change account settings.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example output presents reset times specifically in America/Los_Angeles, which can imply a fixed locale/time-zone behavior. The policy requires avoiding forced locale assumptions unless the skill offers user choice or clearly documents why the locale is fixed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This markdown skill describes a fallback that reads ~/.claude/stats-cache.json, which is a local user data file, but it does not warn that the skill may inspect local cached usage information. For markdown files, the guidance should disclose behaviors that may affect user data or privacy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.