ClawHub
Back to skill

Security audit

CPA

Security checks for vulnerabilities and agentic risk

Overview

This CPA exam skill is a disclosed study-planning and progress-tracking helper with local file storage that fits its stated purpose.

Before installing, be aware that the skill may maintain CPA study and exam records in ~/cpa/. Keep sensitive score reports, calendar details, education records, and student data out of the tracker unless you are comfortable storing them locally, and verify CPA requirements with official state board sources because rules can change.

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
96% confidence
Finding
The skill explicitly instructs the agent to maintain tracking data under ~/cpa/passed/, which implies creating or modifying files in the user's home directory without any explicit consent, disclosure, or safety constraints. Even though the data is low sensitivity, silent filesystem writes can violate user expectations, create persistence, and normalize broader unauthorized local-state changes by agents.

Static analysis

No suspicious patterns detected.