ClawHub
Back to skill

Security audit

Java基础版

Security checks for vulnerabilities and agentic risk

Overview

This is a Java code review and generation helper with broad tool declarations, but the inspected artifact shows no hidden, destructive, persistent, or exfiltrating behavior.

Install this if you want an agent to review or generate basic Java code. Be aware that it declares write and exec capabilities, so only use it in projects where you are comfortable with the agent editing files or, if you allow it, running Java-related commands.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill advertises itself as a Java code review/generation aid, but it also requests exec capability without narrowly justifying why command execution is necessary. In an agent environment, unnecessary exec access expands the attack surface and could enable arbitrary command execution if user-controlled file paths or generated instructions are later passed to shell commands.

Intent-Code Divergence

Medium
Confidence
84% confidence
Finding
The documentation says the skill is instruction-driven and requires no extra API key, yet it later treats command execution failure as a normal operational condition. This inconsistency suggests hidden or under-specified execution behavior, making it harder for users and reviewers to understand when the skill may affect the host system.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes write and exec capabilities but does not warn users that it can modify files or run system-affecting actions. When paired with loosely scoped code-review functionality, this can mislead users into invoking a skill that has far more power than its description implies.

Static analysis

No suspicious patterns detected.