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 Chinese-language historical knowledge skill with broad topic triggers, but it contains only Markdown/JSON reference material and no hidden code, persistence, or data access behavior.

Install this if you want a Chinese-language reference skill for Reinhard's European expansion/global history framework. Be aware that its activation terms are broad, so agents may cite it during general colonialism or global-history conversations even when you did not explicitly ask for this book-specific framing.

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
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 (20)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README states the assistant will 'automatically recognize and cite this skill' for broad natural-language prompts, which can cause unintended activation outside explicit user opt-in. In a knowledge skill, accidental triggering can bias responses, inject copyrighted or domain-specific material when not requested, and override other more appropriate skills or the user's language/context preferences.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: Declaring the skill as 'Chinese-first' without a user language choice or opt-in can cause the agent to respond in an unexpected language, reducing user control and increasing the chance of misunderstood outputs. While this is not a code-execution risk, it is a genuine safety and usability issue because it can silently override platform or user language preferences during activation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description says the skill activates whenever the user discusses broad topics such as colonialism, imperialism, decolonization, global history, and related subjects. These are wide academic and conversational domains, so the trigger overlaps with many ordinary discussions that may not specifically require this book-based skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description is entirely in Chinese and presents the skill as a Chinese-language knowledge resource, but it does not say that language is optional or user-selectable. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill defines automatic activation for a very broad set of common history and international-relations topics without clear exclusion rules. In an agent environment, this can cause unintended invocation, pulling in this skill's framing and instructions in contexts where the user did not request it, which may override user intent, degrade answer quality, or create prompt-scope confusion across adjacent topics.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This markdown file presents all instructions and analytical guidance exclusively in Chinese, with no indication that the user can choose another language or that the skill is intentionally region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: 该 markdown 文件全文以中文编写，未见任何说明这是面向特定中文用户群体的限定内容，也未提供语言选择或用户 opt-in。根据规则，若技能内容强制特定语言而无用户选择，属于自然语言层面的语言/locale 策略问题。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file's title and all instructional/content text are written exclusively in Chinese, with no indication that users may choose another language or that the chapter is intentionally restricted to a Chinese-language audience. The policy specifically flags language or locale constraints when they are imposed without user choice or explicit justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This file contains natural-language instructional content exclusively in Chinese, and there is no indication that users can opt into another language or that the chapter is intentionally restricted to a Chinese-language audience. Under the policy rule, forcing a specific language without user choice 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 markdown file forces a specific language/locale for the entire skill content, which matches the policy category for language or locale violations. There is no indication that the user can choose another language or that the Chinese-only presentation is a documented, justified regional constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This markdown file presents the skill content entirely in Chinese and does not offer any language or locale choice to the user. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the constraint is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest explicitly sets the skill language to "zh-CN", which can constitute a language/locale policy issue when no user choice or opt-in is indicated elsewhere in the file. This may constrain interaction language by default rather than offering a selectable locale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. In these lines, the document presents terms such as "Vertrag von Tordesillas" and "Heinrich der Seefahrer" inline in a Chinese document without any user opt-in or stated reason for forcing that locale choice, which can conflict with a policy of respecting the user's language context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file presents all instructional content in Chinese and does not indicate that the user can choose another language or that the locale is intentionally restricted for a documented regional purpose. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file contains natural-language content that effectively forces a specific language/locale for all users. Under the policy, language constraints should either be optional for the user or clearly documented as justified for a region- or language-specific use case.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file contains natural-language instructional content exclusively in Chinese, and there is no indication that the user can choose another language or that the chapter is intentionally restricted to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The entire skill file is written in Chinese and does not indicate that language selection is optional or that the content is intended only for a Chinese-language audience. Under the policy rule for language or locale constraints, this can be a natural-language policy issue when no opt-in or justification is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file’s title and all instructional/content text are written exclusively in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy, forcing a specific language without opt-in is a natural-language locale violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: SQP-3 applies to all file types and covers natural-language language or locale policy violations. Line L40 explicitly describes '俄语强制推广' (forced promotion of Russian), presenting a language-imposition framing without any user choice or neutralizing context in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: Line L52 states that colonial languages such as English, French, and Portuguese became official languages and literary media. In a policy-audit context, this is the only plausible language/locale-related issue because it normalizes specific languages without any opt-in framing, even though the file is largely analytical rather than instructional.
Content: No source excerpt is available for this finding.