Security audit

Exam

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only exam prep skill whose storage and reminder behavior is mostly disclosed and aligned with its study-tracking purpose.

Before installing, be aware that the skill may keep study questions, flashcards, session history, and performance stats locally under ~/exams/. Use care with sensitive notes or proprietary exam materials, and only allow cron reminders after reviewing exactly what scheduled job will be added and how to remove it.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill explicitly describes persisting questions, session history, performance statistics, and flashcards under a local filesystem path without disclosing that user-provided study material and behavioral data may be written to disk. This can expose sensitive notes, exam materials, or personal performance data to unintended local access, backup sync, or later reuse without the user's informed consent.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill says reminders at 7pm daily use cron, which implies modifying the user's scheduled tasks, but it does not warn the user or require explicit consent before changing system configuration. Silent or ambiguous cron creation is dangerous because it creates persistence on the host and can surprise users, conflict with existing jobs, or be abused by an execution-capable agent framework.

Vague Triggers

Low

Confidence: 85% confidence
Finding: The markdown lists short natural-language commands such as "Quiz me on [topic]" and "Show my weak areas" without clarifying whether these are exact trigger phrases, examples, or only valid within a specific invocation context. Because the skill does not provide exclusion conditions or scope limits, ordinary chat about studying could ambiguously resemble activation requests.

Static analysis

No suspicious patterns detected.