Security audit
Security checks for vulnerabilities and agentic risk
This is a writing-style skill for Chinese WeChat long-form articles and does not request code execution, credentials, persistence, or sensitive access.
Install this if you want agents to draft Chinese WeChat-style long-form articles in the Khazix voice. For general writing help, non-Chinese output, or a different tone, tell the agent not to use this style or choose a narrower writing skill.
The skill advertises activation for very broad requests like writing articles, continuing drafts, or producing long-form content from materials. That can cause the agent to invoke this skill in many ordinary writing scenarios without explicit user opt-in, steering responses into a fixed persona and workflow and potentially overriding user intent or more appropriate skills.
The skill is defined as a fixed Chinese WeChat-article writing style and does not indicate that the user must request or approve that locale and stylistic constraint. In an agent setting, this can lead to unwanted language/style coercion, reduced usability, and mismatch with user requirements, though it is not a direct code-execution or data-exfiltration risk.
No suspicious patterns detected.
