ClawHub
Back to skill

Security audit

java-coding-quality

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Java quality-gate helper that runs standard static-analysis tools and makes scoped project changes with consent for persistent configuration.

Install this if you want an agent to run Java static analysis, create a local .qualitygate folder, and potentially fix code until serious findings are cleared. Review before allowing persistent pom/Gradle changes, since those intentionally add quality gates to future builds.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (10)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest says to use the skill after essentially any Java/Spring Boot code writing, modification, refactoring, pre-submit check, code review, scan fixing, or quality/security scan request, including when the user does not mention a specific tool. This creates an ambiguous and very wide trigger scope for a manifest file, with no explicit negative examples beyond a few technology exclusions, increasing the chance of unintended invocation during ordinary Java development requests.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The file presents the skill name and all user-facing instructions in Chinese, but does not state that language choice is optional or user-selected. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless the constraint is explicitly justified and documented.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The natural-language description and comments present the ruleset documentation entirely in Chinese, which can constitute a language/locale policy violation when no user choice or opt-in is offered. The file does not document that this skill is intentionally limited to a Chinese-speaking audience or region-specific context.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
This markdown skill documentation appears to require Chinese comprehension throughout, but it does not state that the skill is region-specific or provide any user opt-in for language preference. Under the natural-language policy rule, forcing a specific language without user choice can be a locale-policy violation.

Hidden Instructions

High
Category
Prompt Injection
Content
priority 语义：1=Blocker(bug/事故) 2=Critical(高风险) 3=Major(规范) 4/5=Minor(风格)。
    </description>

    <!-- ============ 一、异常处理 ============ -->

    <!-- 空 catch 吞异常 -->
    <rule ref="category/java/errorprone.xml/EmptyCatchBlock">
Confidence
70% confidence
Finding
<!-- ============ 一、异常处理 ============ --> <!-- 空 catch 吞异常 --> <rule ref="category/java/errorprone.xml/EmptyCatchBlock"> <priority>1</priority> </rule> <!-- catch 泛型异常/Throwab

Hidden Instructions

High
Category
Prompt Injection
Content
<rule ref="category/java/bestpractices.xml/MethodReturnsInternalArray">
        <priority>3</priority>
    </rule>
    <!-- 构造/方法直接存储传入数组引用 -->
    <rule ref="category/java/bestpractices.xml/ArrayIsStoredDirectly">
        <priority>3</priority>
    </rule>
Confidence
70% confidence
Finding
<!-- 构造/方法直接存储传入数组引用 --> <rule ref="category/java/bestpractices.xml/ArrayIsStoredDirectly"> <priority>3</priority> </rule> <!-- 方法返回 null 而非空集合，调用方须额外判空（NPE 高频根因） --> <rule ref

Hidden Instructions

High
Category
Prompt Injection
Content
<rule ref="category/java/bestpractices.xml/SystemPrintln">
        <priority>3</priority>
    </rule>
    <!-- e.printStackTrace() 应替换为日志框架记录 -->
    <rule ref="category/java/bestpractices.xml/AvoidPrintStackTrace">
        <priority>3</priority>
    </rule>
Confidence
70% confidence
Finding
<!-- e.printStackTrace() 应替换为日志框架记录 --> <rule ref="category/java/bestpractices.xml/AvoidPrintStackTrace"> <priority>3</priority> </rule> <!-- 日志调用前应先检查级别（性能与安全：避免敏感信息拼入被禁用的日志） -->

Hidden Instructions

High
Category
Prompt Injection
Content
<packaging>jar</packaging>

    <properties>
        <!-- 与被检项目一致，探测得到的 targetJdk 填这里 -->
        <maven.compiler.release>17</maven.compiler.release>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>
Confidence
21% confidence
Finding
<!-- 与被检项目一致，探测得到的 targetJdk 填这里 -->

Hidden Instructions

High
Category
Prompt Injection
Content
</properties>

    <build>
        <!-- 包装 pom 在 .qualitygate/ 内，上跳一级指向被检项目源码 -->
        <sourceDirectory>${project.basedir}/../src/main/java</sourceDirectory>
        <plugins>
            <plugin>
Confidence
21% confidence
Finding
<!-- 包装 pom 在 .qualitygate/ 内，上跳一级指向被检项目源码 --> <sourceDirectory>${project.basedir}/../src/main/java</sourceDirectory> <plugins> <plugin> <groupId>org.apache

Hidden Instructions

High
Category
Prompt Injection
Content
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <!-- Agent 操作：从被检项目 pom.xml 复制 <dependencies>（compile + provided 作用域）至此。
         使 SpotBugs 能解析第三方类型，减少 missingClasses 误报。
         项目无第三方依赖时可省略此段。 -->
    <dependencies>
Confidence
21% confidence
Finding
<!-- Agent 操作：从被检项目 pom.xml 复制 <dependencies>（compile + provided 作用域）至此。 使 SpotBugs 能解析第三方类型，减少 missingClasses 误报。 项目无第三方依赖时可省略此段。 --> <dependencies> <!-- 示例（按实际项目 pom 填入

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.