ClawHub
Back to skill

Security audit

Java代码审查免费版

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a Java code review helper, but its routing and capability text is broader than its stated purpose and includes unclear mutation-related authority.

Review this skill before installing and use it only for Java code review tasks. Avoid granting write or deployment authority unless you explicitly want the agent to modify files, and check any generated fixes before applying them.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Description-Behavior Mismatch

Medium
Confidence
90% confidence
Finding
The skill is presented as a Java code review tool, but its capability section broadens into generic create/query/update/delete, import/export, save, and conversion operations. This scope drift can cause an agent to invoke the skill in contexts beyond code review, increasing the chance of unintended file or workflow actions under a misleading description.

Vague Triggers

High
Confidence
95% confidence
Finding
The top-level description says to use the skill for broad activities such as code generation, programming assistance, debugging, testing, and deployment, far beyond Java code review. Overbroad routing language can cause the agent to select a skill with exec/write-adjacent expectations in many common development scenarios, expanding attack surface and enabling inappropriate tool use.

Vague Triggers

High
Confidence
94% confidence
Finding
The activation condition is vague and says the skill should be used for code generation, programming assistance, debugging/testing, and deployment whenever needed. Such ambiguity makes the skill eligible for a wide range of routine prompts, which is risky in a skill that advertises executable tooling and inconsistent scope.

Static analysis

No suspicious patterns detected.