Back to skill

Security audit

舟谱订单导入

Security checks for vulnerabilities and agentic risk

Overview

This is a local Excel template generator for Zhoupu order imports; it has documentation rough edges, but no hidden network, credential, persistence, or destructive behavior was found.

Install only if you use this specific Zhoupu Chinese-language order workflow. Review generated spreadsheets before importing, especially quantities, barcodes, units, prices, and the self-pickup output columns, because the documentation and generated column count do not fully match.

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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

主要不一致点在于声明描述了同时涉及“自提订单+调拨订单分开”的订单导入模板生成能力,但该代码从标题、sheet名、输出文件名、字段规则到主流程都明确只处理“自提订单”。没有任何调拨订单生成、拆分到另一表、或双类型输出的逻辑。另一方面,描述虽然提到把下单表转成舟谱可导入Excel,这一点与代码基本一致;代码确实生成Excel模板,且只有1个sheet,也符合部分描述。但实际实现比声明更具体:它不仅转换格式,还依赖价格表、补充价格、按客户映射价格列、生成单价并进行数量/必填校验。因此应判定为描述与实际行为存在实质性不匹配,核心原因是缺失了声明中的“调拨订单”能力。

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

该代码的主功能与描述部分重合,但范围明显更窄。描述宣称是“订单导入模板生成(自提订单+调拨订单分开)”,暗示支持两类订单;而实际代码文件名、参数说明、sheet标题、字段设计和处理逻辑都只针对“调拨订单”。代码没有任何自提订单分支、输出结构或相关处理逻辑。因此属于描述覆盖范围大于实际行为的功能性不一致。除此之外,代码未表现出其他未声明的敏感能力;读取Excel、价格表匹配、生成导入文件、校验统计都属于该已声明目的的实现细节。

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
90% confidence
Finding

The entire skill description and operating instructions are written only in Chinese, including the manifest description and all user-facing workflow guidance. This can constitute a language/locale policy issue because the skill effectively requires a specific language without an explicit user opt-in or a documented regional justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

文件头注释在L009明确写明“模板字段(9列)”并列出9个字段,但generate_excel在L309-L330实际定义并输出了19列完整模板。这里不是简单的文档省略,而是对输出格式的核心描述与实际行为直接不一致,可能误导调用方对生成文件结构的理解。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file contains user-facing natural-language instructions entirely in Chinese, including the module description and usage/help text. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script's print messages, warnings, and status outputs are presented only in Chinese throughout execution. This enforces a single language for operational interaction and error handling without any language selection mechanism or documented locale justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The top-level natural-language documentation is entirely in Chinese and presents usage and operating rules only in that language. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative or justification is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.