Back to skill

Security audit

生成读书活动

Security checks for vulnerabilities and agentic risk

Overview

This skill generates reading-activity documents and writes them locally; its file actions are disclosed and scoped to generated output, with no evidence of credential access, remote code, persistence, or hidden behavior.

Before installing, confirm that you are comfortable with the skill creating files under E:\Temp\ReadingActivities and packaging generated outputs into a zip. The documented workflow uses .xls filenames even though the helper rejects .xls, so the publisher should fix that format mismatch for reliability.

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
  • 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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

声明的技能核心目的是基于书名生成读书活动及相关文档内容,而实际代码只是一个通用的 Excel 导出工具:接收文件路径和数据字典,构造 DataFrame 后写入 Excel 文件。它既不处理书名,也不生成活动方案、打卡计划或题库内容。虽然“生成文档”可能间接需要导出文件,但该代码片段本身只覆盖存储环节,和声明的主要功能存在明显偏差,因此应判定为描述与行为不匹配。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to create directories and files, compress them, and then delete the originals by moving them to the recycle bin, but it does not require explicit user consent or clear warning before making these filesystem changes. This is dangerous because a user may invoke a content-generation task without realizing it will persist data locally and alter the filesystem, which can lead to unwanted data storage, overwrite/confusion risks, and privacy issues if book titles or generated content are sensitive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language strings in the docstring and return values are exclusively in Chinese, which imposes a specific language choice on users without offering an alternative or opt-in. This can violate language or locale policy when a skill is expected to be generally usable across users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language description, trigger examples, workflow responses, and edge-case messages are all specified only in Chinese, with no indication that users may choose another language. This can violate a language/locale policy when no opt-in or documented regional limitation is provided.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The function writes data to the filesystem with df.to_excel(filePath, index=False), which can overwrite or create files, but there is no confirmation prompt or explicit warning about this side effect. The docstring describes saving a file, but it does not caution about potential overwrite or data impact.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.