Security audit

技术解释器（当你发来一句或一段包含技术名词的文本时，自动识别其中的专业术语，用"是什么 → 解决什么问题 → 通俗比喻"的三步法，为没有技术背景的小白逐个解释每一个陌生词汇。）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language technical term explainer with no code execution, network access, persistence, or credential handling in the inspected artifacts.

Install this if you want Chinese, plain-language explanations of technical terms. Be aware it may activate on broad AI or programming explanation requests and may not be suitable for users who expect English responses.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill is written to respond in Chinese without indicating language negotiation or fallback behavior, which can create unsafe or misleading interactions when the user’s preferred language differs. While not a classic security flaw, this can undermine informed consent and accurate communication, especially if the user misunderstands explanations or cannot verify the output.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger scope is broad enough to activate on many ordinary explanation requests involving AI, programming, or technical terms, which can cause the skill to intercept requests outside a narrowly intended domain. Over-broad activation is risky because it can override more appropriate system behavior, increase unintended data handling, and make routing/policy enforcement less predictable.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The file title and introductory text present the content only in Chinese, with no indication that language choice is optional or that the document is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in can be a natural-language locale violation.

Static analysis

No suspicious patterns detected.