Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only novel-writing helper with minor scope and language ambiguity but no evident security-impacting behavior.
Install this if you want a Chinese-oriented fiction planning assistant. Users who expect strict activation boundaries or non-Chinese output may want clearer language preferences, but there is no artifact-backed indication of malicious behavior.
The skill description is broadly triggered by generic novel-writing requests, which can cause the agent to invoke this skill in many loosely related contexts. Over-broad routing increases the chance of unintended activation, response hijacking, or bypass of more appropriate specialized skills, reducing predictability and safety controls.
The file mixes English metadata with predominantly Chinese instructional content and presents the skill as a Chinese-language experience by default. There is no statement that users may choose another language, nor any justification that the skill is intentionally limited to a Chinese-language audience or region.
The manifest description uses very broad trigger phrases such as requests to write novels, create plots, design characters, or develop fiction narratives. This can cause the skill to activate for a wide range of generic writing requests, leading to over-broad routing, unexpected invocation, and possible interception of user prompts better handled by other skills or base assistants.
The description begins in Chinese and then switches to English for invocation guidance, but it does not state whether the skill should operate in a specific language or let the user choose. This can create an implicit language/locale constraint without user opt-in, which is a natural-language policy concern.
No suspicious patterns detected.
