Security audit

告别不规范代码，让 AI 成为你的代码质量守护者

Security checks for vulnerabilities and agentic risk

Overview

This skill is a code-style assistant that reads limited project metadata to choose local coding rules, with no evidence of network access, destructive actions, or persistence.

Install this if you want a Chinese-language coding-standards helper that inspects ordinary project metadata to choose rule guidance. Be aware that it may activate on broad coding requests, some advertised stacks lack shipped rule files, and its guidance is not localized outside Chinese by default.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (18)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The code chunk’s primary behavior is technology-stack detection and recommendation generation. It reads local project metadata and source file extensions to infer languages/frameworks, then returns a list like '加载 TypeScript 规范'. This partially aligns with the description’s claim of auto-identifying the tech stack, but it does not implement the broader declared capabilities: generating standards-compliant code, reviewing existing code for standards violations, repairing code, or initializing/configuring code-rule setups. The actual scope is a narrower supporting component for such a system, not the full '智能代码规范助手' as described.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are overly broad and overlap with common coding requests such as '生成代码' and '代码审查', which can cause the skill to activate in many unrelated contexts. That increases the chance of prompt hijacking at routing time, unintended instruction precedence, or the assistant applying this skill when the user did not ask for standards enforcement, leading to incorrect or unsafe task handling.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill is written entirely in Chinese and presents its role, workflow, and output format in Chinese without indicating that the user may choose another language. This can constitute a language/locale policy violation because it implicitly fixes the interaction language rather than offering opt-in or user preference selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: Natural-language policy checks apply to all file types. Several message and template strings are written only in Chinese, with no indication that the user can choose another language or that the locale restriction is intentional and justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: This is a JSON manifest file, so vague-trigger checks apply. The promptTemplates list contains broad instructional phrases but does not specify when these prompts should be applied, what contexts they are for, or any exclusions, which can cause the skill to match too broadly in general Next.js discussions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The promptTemplates array defines user-facing guidance entirely in Chinese. Without an opt-in or documented regional scope, this constitutes a language policy concern because the skill may impose a specific locale on users.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This JSON manifest contains multiple natural-language rule strings in Chinese that prescribe how the skill should behave, such as prop marking and default prop guidance. Because the file enforces a specific language/locale in its instructions and does not offer any opt-in or alternative language option, it may violate language-choice policy for general-purpose skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The promptTemplates and fileTemplates embed instructional text exclusively in Chinese, which suggests generated guidance or templates will be presented in that locale by default. The file does not state that users can choose another language or that the locale restriction is intentional and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This JSON file contains multiple natural-language messages in Chinese, such as the guidance at L16-L17, while other parts of the file are in English. That creates a language/locale policy concern because the skill imposes a specific language on users without any visible opt-in or explanation that the skill is intended only for a Chinese-speaking context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The message at L27 is user-facing natural-language guidance in Chinese, but the file does not indicate that users can choose their language or that the skill is region/language-specific. Under the policy, forcing a specific language without opt-in is a reportable violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The promptTemplates array contains multiple Chinese-language instruction strings that would shape the skill's output behavior. Because the file provides no alternate locale or opt-in mechanism, this is a natural-language policy violation for enforcing a specific language.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 80% confidence
Finding: This JSON manifest defines language and framework activation via generic file-presence markers such as "package.json", "requirements.txt", and "pom.xml". Several of these are common across many projects, and the manifest does not document exclusion conditions or negative examples, which can make skill selection ambiguous or overly broad.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This JSON file contains multiple natural-language rule messages and prompt templates exclusively in Chinese, such as at L10 and throughout the promptTemplates block. Because the skill appears to define general Go-language guidance rather than a clearly China-specific or opt-in locale-specific tool, this enforces a specific language without documented user choice, which is a locale policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This JSON manifest contains user-facing rule messages in Chinese, indicating the skill's guidance is fixed to a specific language. The policy requires flagging language or locale constraints when the skill forces a specific language without opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The promptTemplates array defines all guidance in Chinese, which constitutes a natural-language policy concern if users are not given a language choice. No surrounding metadata explains that this is a region-specific or Chinese-only skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This JSON rule file contains multiple user-facing messages and prompt templates exclusively in Chinese, such as the guidance strings in the rules and promptTemplates sections. Because the file does not indicate that Chinese is optional or that the skill is intended only for a Chinese-language context, it appears to impose a specific language without user 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 code embeds its primary natural-language description and user-facing recommendations in Chinese, indicating the skill is intended to operate in a fixed language/locale. The file does not offer any user opt-in, language selection, or justification for being Chinese-only, which creates a language policy issue under the natural-language policy rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description uses Chinese-language text ("CodeRules 规范库索引") without any indication that users may select their preferred language or locale. Under the policy, hard-coding a language in natural-language metadata can be a locale-policy issue unless the constraint is explicitly justified or optional.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.