Security audit

java-standards-alibaba

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Java standards skill that may be overbroad or inconvenient, but it does not show hidden execution, data access, persistence, or exfiltration behavior.

Install this only if you want Alibaba Java Development Guidelines applied broadly to Java work. Expect Chinese documentation and strict style recommendations; override the skill when a repository has different conventions or when database changes require stronger human review, backups, or transactions.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (31)

Vague Triggers

High

Confidence: 95% confidence
Finding: The skill declares that it will auto-activate for essentially any Java coding, review, or modification scenario, which is an overly broad trigger surface. This can cause the skill to steer unrelated tasks, override more specific user intent, or apply heavy-handed policy behavior in contexts where it was not explicitly requested, increasing the chance of unsafe or unintended agent behavior.

Ae1

High

Category: analysis-evasion
Content: | MyBatis / ORM 映射 | [references/orm.md](references/orm.md) — ORM 映射 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | MyBatis / ORM 映射 | [references/orm.md](references/orm.md) — ORM 映射 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 项目分层 / 依赖 | [references/project-structure.md](references/project-structure.md) — 工程结构 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Ae1

High

Category: analysis-evasion
Content: | 项目分层 / 依赖 | [references/project-structure.md](references/project-structure.md) — 工程结构 |
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The README is written entirely in Chinese and states enforcement of a specific guideline set without indicating any user language preference or opt-in. In an agent setting, this can create usability and transparency issues: users may not understand what rules are being applied, and hidden language assumptions can lead to incorrect acceptance of generated code or missed review findings.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description says it activates for any Java code generation, review, or modification task, which is overly broad and can cause the skill to engage in many unrelated contexts. Overbroad activation increases the chance that the agent follows unnecessary workflow steps, loads excess context, or applies instructions where they were not intended, weakening isolation and predictability.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The skill body is written as mandatory instructions in Chinese and states the规范 must be strictly followed in all Java writing, modification, and review scenarios. The file does not offer a language choice or indicate that Chinese output is optional, which can violate language/locale choice expectations.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The automatic activation section lists many broad scenarios but does not define boundaries, precedence, or exclusion conditions. This ambiguity can lead to unintended invocation on routine tasks, causing instruction overreach and making agent behavior harder to control or audit.

Context-Inappropriate Capability

Medium

Confidence: 90% confidence
Finding: The skill references a host-specific absolute path (`D:\ai\Java开发手册（嵩山版）.md`) outside the declared in-skill reference set. This creates an undeclared dependency on local filesystem content, which can cause data exposure, non-portable behavior, or unintended access to sensitive host files if an agent attempts to satisfy the instruction literally.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The document title and all instructional content are presented only in Chinese, which imposes a language choice on users. Under the policy, forcing a specific language without opt-in or a documented justification is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The markdown explicitly states '中文注释优先', which imposes a language preference on users. Under the policy, forcing a specific language without user opt-in or a clearly justified regional constraint is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file contains natural-language guidance exclusively in Chinese, and there is no indication that users can opt into another language or that the content is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in is a reportable issue.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The title and all instructional content are written in Chinese, and the file provides no indication that language choice is optional or that this is a region-specific skill with a documented justification. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Missing User Warnings

Medium

Confidence: 83% confidence
Finding: This markdown instructs users on deleting or modifying records and only advises running a SELECT first. While that is a safety check, it does not explicitly warn that these actions can irreversibly affect user data or recommend confirmation/backup steps.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: Lines L013-L019 state that programming-related names must not use Chinese and must not mix pinyin with English, which is a language policy constraint expressed in natural language. Because the rule is framed as a blanket prohibition rather than a justified region-specific requirement or user choice, it fits the language/locale policy violation category.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The title and entire document are presented as a normative specification in Chinese, with no indication that users may choose another language or that the locale restriction is required for a region-specific purpose. This can violate the language/locale policy rule because it effectively forces a specific language without opt-in.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The document states that front-end and back-end time formats must be unified to a specific format and to GMT. Under the policy criteria, forcing a locale/timezone convention without offering user choice or documenting a region-specific justification is a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: This markdown file is entirely written in Chinese and presents its guidance as the default skill content, with no indication that users may choose another language or that the scope is intentionally limited to Chinese-speaking users. Under the policy rules, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: The entire skill document is written in Chinese and does not provide any indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: This markdown file contains user-facing instructional content only in Chinese, and there is no note that the skill or reference is Chinese-only by design, nor any opt-in for language preference. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This markdown file presents all guidance in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. The policy for natural-language violations applies to all file types and specifically covers forcing a language without user opt-in.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: This markdown file contains instructional content exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: The markdown states that log error information should be described in English for international teams or overseas deployments, with Chinese only as a fallback. This imposes a language preference in the guidance without presenting it as a user or operator choice, which matches the language/locale policy violation category.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The file title and all instructional content are presented exclusively in Chinese, which can constitute a language-policy issue when a skill mandates a specific language without user opt-in or an explicit region-specific justification. The document does not state that the skill is intended only for Chinese-speaking users or offer an alternative language choice.

Static analysis

No suspicious patterns detected.