Back to skill

Security audit

teacher-prep

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese primary-school lesson-prep helper that performs purpose-aligned searches and creates local teaching files, with some quality and disclosure gaps but no evidence of malicious behavior.

Install only if you want a Chinese-language elementary lesson-prep workflow. Expect Tavily web searches and local files named like 备课资料_<课文名>.md, 教案_<课文名>.pptx, and 练习题_<课文名>.docx; avoid sensitive student or proprietary content in searches, and review generated materials because the bundled scripts produce templates rather than complete lesson-specific answers.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是一个完整的备课助手,核心能力包括资料检索、备课资料生成、PPT 生成以及练习题与答案生成。而代码行为明显更窄:它只本地创建 .docx 文档,按课文类型写入固定练习题模板,并在答案部分留下“教师根据实际教学情况填写参考答案”的占位说明。代码没有任何网络搜索、外部资料读取处理、markdown 输出、PPT 生成或答案自动生成逻辑。虽然“生成 Word 格式课后练习题”这一点与声明部分吻合,但整体上代码仅覆盖声明中的一小部分,且连“参考答案”也未真正生成,因此描述与实际行为存在实质性不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明描述的是一个完整的教师备课助手,核心能力包括资料搜索、备课资料整理、PPT 生成和练习题/答案文档生成,并且表述为会自动执行这些步骤。实际代码仅实现了其中一小部分:生成教案 PPT,而且内容是固定教学模板,只有标题和少量文本随输入变化。代码没有网络搜索、文件检索、内容解析、markdown 输出、Word 输出或答案生成逻辑。虽然“生成教案PPT”这一点与声明部分一致,但声明的主要功能集合并未被该代码体现,因此描述与实际行为存在实质性不匹配。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill description is written as a Chinese-only elementary language-teaching assistant and presents its behavior entirely in Chinese without stating that language output is optional or configurable. Under the language/locale policy, forcing a specific language without user opt-in can be a policy concern unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly describes automatic generation of multiple output files, but does not warn users that invoking it will create and save artifacts on disk. In agent environments, unexpected file creation can overwrite existing work, leak sensitive lesson content into shared workspaces, or surprise users who expected a read-only assistive action.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs use of Tavily for external searches but does not disclose that user-provided lesson requests or document details may be sent to a third-party service. In an education context, prompts may contain unpublished teaching materials, student-related context, or proprietary content, so undisclosed external transmission creates a real privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill automatically generates 'Word格式课后练习题及参考答案', implying substantive exercise content and answers derived from the lesson. In this file, the questions are fixed generic templates and the '参考答案' section explicitly says '教师根据实际教学情况填写参考答案', so the implemented behavior falls short of the claimed automatic generation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The module docstring and CLI usage indicate a third argument '[备课资料文件路径]', which implies the document generation may use that file as input. However, although 'content_file' is accepted and passed through, it is never read or used anywhere in the implementation, contradicting the documented intent of that argument.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file-level description and generated content indicate the skill always produces Chinese teaching PPT content and Chinese-language CLI messaging. This is a natural-language locale constraint with no user opt-in or documented justification that the skill is region- or language-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.