Security audit

College Exam Sprint

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language study-planning skill that organizes exam revision materials and progress records without executable code, network behavior, or hidden privileged actions.

Before installing, confirm you want a Chinese-language exam sprint workflow and keep any private course files inside the disclosed study workspace. Review generated plans, records, and quizzes yourself, especially where academic integrity rules apply.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill name and full description are written in Chinese and the documented user interaction patterns are Chinese-only, but the file does not state that language is optional or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The file defines very broad natural-language triggers such as “讲一下”, “给个例题”, “我这里没懂”, and “开始今天任务”, which are common phrases in ordinary educational conversation. This can cause the skill to activate or take over behavior unexpectedly during unrelated or mixed-context chats, leading to unintended instruction routing, loss of user intent fidelity, or interference with other safeguards and agent workflows.

Static analysis

No suspicious patterns detected.