ClawHub
Back to skill

Security audit

Quiz

Security checks for vulnerabilities and agentic risk

Overview

This is a quiz-design guidance skill with no executable code; its privacy-sensitive quiz advice should be applied carefully but is not unsafe by itself.

Installation is reasonable for quiz-writing help. Before using its implementation advice in education, hiring, certification, health, minors, or other sensitive settings, add privacy notices, consent where required, data minimization, retention limits, access controls, accommodations, and appeal paths for proctoring or identity checks.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The high-stakes anti-cheating section recommends AI/human proctoring, browser lockdown, and identity verification without warning about surveillance, biometric/identity data handling, false positives, accessibility issues, or device-impact concerns. This could push implementers toward invasive controls that create privacy, discrimination, and operational risk disproportionate to the use case.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The analytics guidance encourages collection of user-level quiz performance, timing, retake behavior, and outcome correlation without any privacy, minimization, retention, or consent safeguards. In a quiz skill, this can lead implementers to collect identifiable behavioral and educational data unnecessarily, creating avoidable privacy and compliance risk.

Static analysis

No suspicious patterns detected.