Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese creative-writing skill for cultivation novels and does not request risky access, persistence, code execution, or hidden data handling.
Install this if you want Chinese-language cultivation-novel writing help. Be aware it may activate on broad genre terms, so users discussing the genre analytically may need to clarify when they do not want creative generation.
The trigger list consists of very broad genre terms such as 修真、修仙、仙侠 and related common vocabulary, which can cause the skill to activate in many loosely related conversations. Overbroad activation increases the chance of unintended prompt injection surface or inappropriate takeover of user requests, even though the skill itself is content-generation focused rather than system-modifying.
The trigger list consists of very broad genre terms like 修真、修仙、仙侠、功法 and related nouns, with no clear activation boundaries, exclusions, or requirement to confirm user intent first. This can cause the skill to activate in loosely related conversations and steer outputs unexpectedly, increasing prompt-injection surface and causing inappropriate skill invocation, though the domain here is creative writing rather than a high-risk operational task.
The manifest description and the entire instruction set are written as a Chinese-only skill, and the examples and trigger terms assume Chinese-language interaction. There is no indication that users may opt into another language or locale, which can be a language-policy issue when the skill is otherwise general-purpose.
No suspicious patterns detected.
