Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent Chinese-language alternate-history roleplaying skill with only low-risk local game-state behavior.
Install this if you want a Chinese-language historical roleplay game and are comfortable with broad history prompts potentially starting game mode. The only persistence found is local game progress in the skill's own data/state.json file.
声明描述的是一个较完整的“历史推演聊天游戏”，包含多个具体机制与触发意图；而实际代码只是一个辅助工具类，负责数值演化、少量事件生成和结局评分，并未实现所述的大部分核心玩法机制或聊天交互流程。此外，代码还会读写本地 state.json，属于声明中未提及的持久化能力。虽然‘推演历史演变’与描述方向相关，但实现范围明显更窄，且存在未声明能力，因此应判定为不匹配。
The README presents the skill entirely in Chinese and does not state that the language is optional, user-selectable, or limited to a justified region-specific context. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.
The trigger phrases include very generic language such as '推演历史', '我想改变历史', and date-based prompts like '从1918年开始', which can easily overlap with ordinary educational or analytical history conversations. This can cause unintended skill activation and steer users into a political roleplay context when they did not explicitly request the game, increasing prompt hijacking and context-confusion risk.
Without declared permissions the skill's intent is opaque and cannot be validated.
The trigger phrases are broad enough to match ordinary discussion about history, politics, or counterfactuals, which can cause the skill to activate unexpectedly outside clear user intent. That can override normal conversation flow and steer users into a specialized simulation mode without an explicit opt-in boundary.
Repeating ambiguous triggers in the usage section reinforces activation on common phrases like '推演历史' or '从 XX 年开始', which may occur in benign educational or conversational contexts. This increases the chance of unintended invocation and prompt-routing errors, especially because the skill concerns broad, high-frequency topics like history and politics.
This markdown file is natural-language documentation, and its title and all subsequent instructions are presented only in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.
This markdown file contains user-facing instructional content exclusively in Chinese, which can amount to a language/locale policy violation when no opt-in, alternative language option, or justification is provided. The policy specifically calls for flagging skills that force a specific language without user choice.
The skill content is written entirely in Chinese and the interaction flow assumes Chinese-language use without presenting a language or locale choice. This can exclude or confuse users who operate in other languages, increasing the risk of misunderstanding instructions, consent, or game outputs, but it does not by itself enable code execution, data exfiltration, or privilege abuse.
The module docstring is entirely in Chinese and presents the skill description in a single fixed language. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.
No suspicious patterns detected.
