Security audit

征服世界：欧洲扩张全球史知识库

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language history knowledge-base skill with no executable code, credential handling, network behavior, or destructive actions.

Install this if you want a Chinese-language reference skill for Reinhard's European expansion history framework. Be aware it may be invoked for broad colonialism or global-history questions, so review answers for framing bias and ask the agent to avoid the skill when you want a general or different-source answer.

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)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: README encourages broad natural-language activation for common history and international-relations queries, which can cause the skill to be invoked outside the user's explicit intent. In a knowledge skill this is not code-execution dangerous, but it can still create scope overreach, unwanted context injection, and incorrect reliance on the book's framework for general questions.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill is configured to auto-activate on a wide range of common history and international-relations topics, which can cause unsolicited context injection into many conversations. While not code-execution dangerous, this broad trigger surface can steer answers, override user intent, and increase the chance of inaccurate or policy-bypassing use of the skill in situations where the user did not explicitly request it.

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The metadata and behavior are written entirely in Chinese and describe activation/usage patterns without offering language negotiation, which can implicitly force Chinese-language interaction regardless of the user's preferred language. This is primarily a safety and usability issue: it can cause confusion, misinterpretation, and unwanted language switching that degrades transparency and user control.

Static analysis

No suspicious patterns detected.