Security audit

Java Development Manual

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese Java development manual with no executable code, persistence, credential handling, or hidden runtime behavior.

Install this skill if you want Chinese-language Java development conventions. Be aware that it may be invoked by broad Java-adjacent terms, and treat the test examples as patterns to review rather than code to copy directly into a live database-backed project.

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 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 (10)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill declares very broad trigger phrases such as “安全”, “MySQL”, “异常处理”, and “设计模式”, which are common terms likely to appear in many unrelated conversations. This can cause unintended activation of the skill, leading the agent to inject irrelevant instructions or context into sessions where the user did not intend to invoke this manual.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The document title and all guidance are written in Chinese, with no indication that users may choose another language or locale. The policy explicitly flags language or locale constraints when a skill forces a specific language without user opt-in.

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The file title and all instructional content are written exclusively in Chinese, presenting the design guidance in a single forced language with no indication of optional language support or user opt-in. Under the stated policy, a skill should not impose a specific language or locale unless it is explicitly documented and justified.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The title and entire document are written in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Per the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This markdown file presents all guidance exclusively in Chinese, and there is no indication that users can choose another language or that the document is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a specific language without opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: This markdown file is written entirely in Chinese and presents mandatory guidance without indicating that language selection is optional. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This markdown file presents all guidance in Chinese from the title onward, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy violation.

Intent-Code Divergence

Medium

Confidence: 89% confidence
Finding: The document states unit tests should avoid external environment dependencies, but the example uses @SpringBootTest with a real application context and invokes the real service in teardown to delete data. This can cause tests to depend on databases, configuration, transactions, and side effects, making the guidance unsafe because users may copy a flaky or destructive testing pattern into production repositories.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: Line L195 states '日志语言：英文优先，说不清用中文', which imposes a language preference as a policy. Under the natural-language policy rule, forcing a specific language without explicit user choice or a documented regional justification is a policy concern.

Intent-Code Divergence

Low

Confidence: 83% confidence
Finding: The sample claims tests should be repeatable and independent of the environment, yet it generates usernames using System.currentTimeMillis(). Time-based dynamic data makes outcomes less deterministic, can hide collisions or race conditions, and undermines reproducibility when diagnosing failures.

Static analysis

No suspicious patterns detected.