Security audit

Excel多表格合并工具

Security checks for vulnerabilities and agentic risk

Overview

This Excel merge skill is mostly a straightforward local workbook utility, but it can copy attacker-controlled spreadsheet formulas into its generated output workbook.

Review before installing if you may process workbooks from untrusted parties. The skill should sanitize names and specifications that begin with =, +, -, @, tab, carriage return, or newline before writing the output workbook. For trusted internal spreadsheets, the core behavior is coherent and local-only.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: merge_script.py:185
Finding: Spreadsheet Formula Injection Through Unsanitized Workbook Values
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: L223-L227 的示例在调用 merge_excel_tables 后打印 len(data_dict)，但 data_dict 是函数内部局部变量，主程序作用域中并不存在，因此该示例无法按注释意图工作。文档将其展示为可直接运行的“使用示例”，这与代码真实行为形成直接矛盾。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This code contains natural-language comments, worksheet titles, headers, and user-facing print messages exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in or a documented locale justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.