Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language AI coding workflow guide with no executable code, install hooks, credential access, persistence, or hidden data handling.
Install this if you want a Chinese guide for structured AI-assisted coding. Be aware it may be selected for broad AI coding workflow questions, and verify any separate tools, APIs, or services you choose to use because this skill only describes them and does not install or run them.
The skill metadata description is written only in Chinese, which may bias routing or downstream behavior toward Chinese output without explicit user preference. While not directly dangerous like code execution or data exfiltration, it can override user language expectations and create an unintended instruction-channel effect.
The trigger section uses very broad natural-language phrases such as requests about AI coding workflows, examples, or how to do VibeCoding, without clear scoping or boundary conditions. This can cause the skill to activate in unrelated conversations and steer the assistant into an unintended workflow, which is a prompt-routing/control issue even though the content is not overtly malicious.
No suspicious patterns detected.
