Back to skill

Security audit

电子书阅读助理

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent ebook reader skill that processes user-provided EPUB/PDF files, with documentation and routing cautions but no evidence of hidden or malicious behavior.

Install only if you are comfortable letting the agent read the full contents of ebooks or PDFs you provide. Avoid confidential, private, or copyrighted files unless you have the right to process them, and confirm the skill is being used for an ebook task when generic reading-note prompts trigger it.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

代码的核心能力是电子书解析,这与声明中的“支持EPUB/PDF等常见格式解析”相符。但声明将技能定位为“智能电子书阅读助手”,并明确包含章节总结、关键内容摘录、深度分析和落地应用建议;这些均未在代码中体现。实际代码只是一个命令行解析工具,按 EPUB 章节或 PDF 页提取文本与元数据并输出 JSON。因此描述显著高估了技能能力,属于描述与实际行为不一致。未发现额外未声明的敏感能力;问题主要在于声明功能多于实际实现。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explicitly encourages users to upload and process full ebook contents, but it does not mention privacy handling, data retention, or copyright constraints. In a skill that ingests entire books, this omission can lead users to submit sensitive personal documents or copyrighted material under unsafe assumptions, increasing the risk of unauthorized disclosure or improper use.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description is written as a Chinese-only assistant description and the rest of the skill instructions are entirely in Chinese, with no indication that the user may choose another language. This creates a natural-language locale policy issue because the skill appears to impose a specific language by default rather than offering user opt-in or language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description and capability text are entirely Chinese-oriented, but the manifest does not declare a locale restriction or user language-selection behavior. This can cause the skill to respond in an unexpected language or be misrouted in multilingual environments, which is a quality and control issue that may interfere with safe, accurate user interactions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes generic phrases such as '读书笔记', '知识转化', and '内容摘录' that can match many ordinary requests unrelated to ebook parsing. This can cause the skill to activate outside its intended scope, increasing the chance of inappropriate routing, unintended file-processing prompts, or user confusion about what tool is handling the request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file title and opening description are entirely in Chinese and present the framework as the required structure for the agent's reading analysis. There is no indication that language selection is optional or that the Chinese-only constraint is limited to a region-specific use case, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions, examples, and outputs are all presented in Chinese, which effectively forces a specific language for interaction. There is no indication that users may choose another language or that the Chinese-only scope is intentional for a region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains user-facing natural-language descriptions and CLI help text in Chinese, but it does not offer users a language/locale option or explain that the tool is intended only for Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The command-line description, argument help, examples, and runtime status/error messages are all presented only in Chinese. Because the file gives no option to select another language and no justification for a Chinese-only locale, this conflicts with the language-choice policy.

Content

No source excerpt is available for this finding.