ClawHub
Back to skill

Security audit

计量器具检定校准到期核对（免费版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local instrument-calibration ledger checker whose file access and execution behavior match its disclosed purpose.

Install only if you are comfortable running a local Node script on calibration ledger/certificate text. It does not verify certificate authenticity online or replace compliance judgment; review its listed excluded checks before relying on the output.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
整体上代码与描述高度一致：核心 6 项检查都已实现，且“材料不足不给结论”也符合。触发语义与计量器具台账/证书核对场景一致，没有发现网络、文件、环境变量等越权行为。 但按严格的描述-行为一致性标准，仍存在轻微到中度偏差。第一，声明重点是 6 项核对，代码却额外利用 #使用记录# 和 #期间核查# 段的数据来自动推导核对基准日，而不是只围绕台账与证书本身；这属于未明确声明的数据利用方式。第二，到期覆盖检查里除“超期即报”外，还附加了“超期器具未列入送检安排”的额外发现项，该能力不在声明的 6 项中。虽然这些扩展仍与业务场景相关，不属于完全无关或恶意功能，但它们是实质性的未声明能力，因此应判定为 mismatch。

Ae1

High
Category
analysis-evasion
Content
跑 `node scripts/run.mjs --sample` 会打印实际执行了哪些检查项，以及**本版本不包含哪些**。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
跑 `node scripts/run.mjs --sample` 会打印实际执行了哪些检查项，以及**本版本不包含哪些**。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Ae1

High
Category
analysis-evasion
Content
跑 `node scripts/run.mjs --sample` 会打印实际执行了哪些检查项，以及**本版本不包含哪些**。
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
This code file contains extensive natural-language instructions, warnings, and output text exclusively in Chinese, including the header comment and user-facing messages returned by the skill. Because the file does not offer user opt-in for language/locale or justify a Chinese-only constraint as region-specific policy, it creates a language-policy violation under the rule.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill’s user-facing description names the capability entirely in Chinese, and the script’s help, errors, and output messages are also presented only in Chinese. This imposes a specific language/locale on all users without any documented opt-in or alternative language selection, which matches the language-policy violation criteria.

Intent-Code Divergence

Low
Confidence
81% confidence
Finding
The manifest and surrounding documentation consistently describe this skill as checking计量器具台账与检定证书材料, not arbitrary contracts. The inline doc/comment at L075 says non-JSON input is treated as plain text material and gives '直接粘贴的合同全文' as the example, which is inconsistent with the declared domain and intent of the tool.

Static analysis

No suspicious patterns detected.