Security audit

Warehouse Network Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed warehouse-analysis helper with quality and accuracy limitations, but no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you are comfortable using it as a lightweight Chinese warehouse-analysis aid. Verify any RDC, coverage, replenishment, and trunk-shipping recommendations independently because the instructions contain contradictory examples and the bundled script implements only basic statistics and distance calculations.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (7)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: 代码的实际功能只覆盖了声明中的一小部分：门店分布统计，以及有限的城市距离测算。它没有实现区域划分建议、报货周期规划、干线发运规划，也没有进行更深入的仓配网络规划分析。虽然不存在明显的额外越权能力或可疑资源访问，代码的实际行为与描述相比明显缩水，属于描述与实现不一致。
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: L207-L220将Step 4描述为基于用户约束、时效和成本进行RDC优化选择；但L274-L289直接规定“每个FSL都是RDC（都需要设仓）”，并在L297-L306给出固定为全部设仓、覆盖率100%的输出示例。这不是信息缺失，而是文档内部对“优化选仓”与“固定全选”两种完全不同策略的主动冲突。
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: L234-L241明确定义“无法连接”为非RDC覆盖，L365-L367也定义覆盖率只包含直接调拨和TC中转；但L300-L306的示例同时列出“无链路（需新增）: 141家 (7%)”并声称“覆盖率: 100%（所有门店都能被配送）”。这构成明确的意图-结果矛盾，会误导使用者理解分析结论。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The note requires chart labels to use English, which is a natural-language locale restriction. The file does not present this as an optional setting or obtain user opt-in, and no clear policy or compliance justification is provided for forcing English labels.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest describes capabilities including city positioning, regional partitioning recommendations, replenishment-cycle planning, trunk transport planning, and support for warehouse/distribution/transfer方案, but this script only reads an Excel file, counts stores by city/province, and computes straight-line distances from a single warehouse coordinate. This is a meaningful description-to-behavior mismatch because the implemented analysis is substantially narrower than the declared planning scope.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The skill explicitly plans to write an output Excel file but does not clearly warn the user that it will modify the workspace or create artifacts. In agent environments, silent file creation can overwrite existing results, clutter shared workspaces, or cause users to disclose or rely on generated files they did not expect.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file’s natural-language interface and output strings are entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-only audience. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.