Back to skill

Security audit

C++课件 → 印象笔记

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it turns course PDFs or Markdown into Yinxiang Note content and can upload it when the user provides a token.

Install only if you intend to give the agent a Yinxiang developer token that can read and write your account. Use a temporary token or environment variable, do not store it in files, verify the target notebook or note GUID before upload/update, and revoke the token afterward.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明中的核心能力是“PDF 提取整理 + 写入印象笔记笔记本”,并特别提到 pymupdf 和扫描页视觉识别。但提供的代码文件是一个独立的 Markdown→ENML 转换脚本,只接收 Markdown 输入文件并输出 .enml 文件。虽然这与声明中“也适用于把 Markdown 转成印象笔记原生格式”的次级场景一致,但它没有体现声明中的主要 PDF 处理与印象笔记写入能力。因此描述对该代码块的实际行为有明显夸大,属于实质性不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明的核心能力是“PDF/Markdown 转为印象笔记超级笔记并写入指定笔记本”,而代码片段的实际职责是本地 PDF 解析与 Markdown 生成。代码使用 pymupdf 提取文本和表格、按字号推断标题、按等宽字体识别代码块、剔除重复页脚和代码行号,并把文字层稀少的页面渲染成 PNG 供后续识别。这与描述中提到的 PDF 提取能力是吻合的,但描述强调的主要输出目标——印象笔记超级笔记原生格式及写入印象笔记——在代码中完全没有体现,也没有任何网络/API 调用、认证、笔记本定位或印象笔记数据结构处理。因此该描述对代码能力有明显夸大,属于实质性不匹配。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

声明的核心能力是“从 PDF/Markdown 生成并整理印象笔记超级笔记”,而该代码片段的实际作用只是“把已经准备好的 ENML 内容写入印象笔记,并设置原生属性”。这不是轻微实现细节差异,而是主功能明显不一致。代码没有出现 pymupdf、OCR、视觉识别、Markdown 解析/转换、课程内容整理等任何相关实现;唯一涉及的资源是印象笔记服务和本地 ENML 文件。因此该描述明显高估了代码能力,构成实质性不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The skill instructs use of environment-backed secrets (YINXIANG_TOKEN) and local file generation/deletion, but it declares no explicit tool scope or permissions boundaries. That increases the chance an agent can access sensitive environment variables or write files more broadly than intended, especially because the workflow handles developer tokens and temporary scripts containing credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, and it does not mention that the skill is China-specific or provide any opt-in for language or locale. Under the language/locale policy rule, forcing a specific language without user choice can be a policy violation.

Content

No source excerpt is available for this finding.