Security audit

设备维保与备件领用费用核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local-only Chinese maintenance-ledger checker that reads user-provided tables and reports arithmetic or completeness issues without network use or persistence.

Install only if you are comfortable using a Chinese-language, local Node-based checker for maintenance and spare-part ledgers. It does not validate warranty facts, read Excel files directly, or perform the paid/full-scope checks it lists as withheld.

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

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 (6)

Ae1

High

Category: analysis-evasion
Content: 跑 `node scripts/run.mjs --sample` 会把实际执行的检查项打印出来；下面这 8 项就是本版本执行的全部：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 跑 `node scripts/run.mjs --sample` 会把实际执行的检查项打印出来；下面这 8 项就是本版本执行的全部：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: 跑 `node scripts/run.mjs --sample` 会把实际执行的检查项打印出来；下面这 8 项就是本版本执行的全部：
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The file’s natural-language instructions, descriptions, and user-facing guidance are all in Chinese, including the contract and usage explanations. This can impose a specific language on users without offering an alternative or explicit opt-in, which matches the language/locale policy violation criteria.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The user-facing documentation, usage text, errors, and runtime output are all hard-coded in Chinese throughout the file. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified or the user is given a choice.

Intent-Code Divergence

Low

Confidence: 87% confidence
Finding: The docstring says non-JSON input is treated as plain text such as a 'contract full text', which contradicts the surrounding manifest and file-level documentation that constrain the skill to equipment-maintenance ledger and spare-parts usage reconciliation. This is not just incomplete wording: it suggests a broader document scope than the skill claims elsewhere.

Static analysis

No suspicious patterns detected.