Security audit

Java Maven Code Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Java/Maven code review helper that reads project files and writes review reports, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Before installing, expect this skill to read the Java/Maven project you provide, including configuration files that may contain secrets, and to create review output files. Use it only on projects you are comfortable exposing to your agent environment, and choose a fresh report filename to avoid overwriting prior reports.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 89% confidence
Finding: The declared description promises a fairly comprehensive Java/Maven code review workflow, including analysis of naming, module boundaries, maintainability, duplicated logic, structure issues, and recommendations, for projects supplied as ZIPs or GitLab URLs. The supplied code chunk only performs a narrow text scan over selected file types using a few hardcoded keyword lists, then writes a report. While this is related to code规范 checking at a superficial level and does produce整改建议-style output, it materially underdelivers on the breadth of analysis claimed. It also depends on an external preparation step for project root and metadata rather than directly processing ZIP archives or GitLab URLs. Therefore the description does not accurately represent this code chunk's actual behavior.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 85% confidence
Finding: The skill declares file read/write behavior but does not define any explicit tool scope such as permissions or allowed-tools. In an agent environment, this can lead to broader-than-expected file access or report-writing behavior, increasing the risk of unintended data exposure or unauthorized file modification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description and usage guidance require Chinese phrases such as 代码规范检查报告 and use Chinese terminology in outputs and triggers, but do not state that this is a China-specific skill or offer the user a language option. This can violate language/locale policy because it implicitly forces a language preference without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This Python file contains user-facing report content entirely in Chinese, including headings, findings, and recommendations. Because the skill does not provide any user opt-in or configurable language selection, it appears to force a specific language/locale, which matches the policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The report template is entirely written in Chinese, including the title and section headings, which implies the skill will generate output in a fixed language. There is no indication that the user can choose the language or that the Chinese-only format is required for a documented region-specific purpose.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill instructs writing a markdown report into the business/ directory without warning the user that a file will be created or potentially overwritten. In agent workflows, silent filesystem modification can cause accidental data loss, confusion, or overwrite of existing business artifacts.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.