ClawHub
Back to skill

Security audit

USMLE

Security checks for vulnerabilities and agentic risk

Overview

This USMLE study skill is coherent and purpose-aligned, with local progress tracking that is disclosed but would benefit from clearer privacy and deletion guidance.

Before installing, be aware that the skill may create and maintain local USMLE records under ~/usmle/ containing exam dates, goals, scores, study logs, question bank progress, assessments, and feedback. This is expected for the skill, but users on shared or managed computers should decide whether that local persistence is acceptable and periodically delete or move the folder if they no longer want it retained.

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly directs storage of persistent user data in ~/usmle/ but does not warn the user that data will be retained locally or describe what categories of potentially sensitive information will be stored. Even though this is study-oriented data, it may include exam dates, performance history, residency goals, and personal profile details that can expose sensitive educational or career information on a shared or unmanaged system.

Static analysis

No suspicious patterns detected.