Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese writing-analysis helper that gives article breakdown instructions and does not include code, network access, credential use, or hidden execution.
Install this if you want a Chinese-language workflow for analyzing article structure and collecting reusable writing patterns. Before letting it write to an Obsidian vault or other library, confirm the exact folder and filename, especially if the article contains private or sensitive content.
The trigger description is intentionally broad enough to activate on loosely related user requests, including cases without an explicit invocation phrase. That can cause the skill to run unexpectedly and steer the assistant into analysis and potential follow-on actions the user did not clearly request, increasing the chance of unintended behavior or consent bypass.
The skill instructs saving output into the user's Obsidian vault by default, but it does not require explicit user confirmation before creating or modifying files. In an agent setting, this can lead to unauthorized persistence of data, accidental workspace changes, or writing sensitive extracted content into user storage without informed consent.
This markdown file presents all instructions and examples exclusively in Chinese, which can constitute a language/locale policy violation when no user opt-in or alternative language option is provided. The document also does not state that it is intended only for a Chinese-speaking or region-specific audience.
No suspicious patterns detected.
