Security audit
Security checks for vulnerabilities and agentic risk
This skill only guides the agent to clarify requirements before implementation, with no code execution, persistence, credential handling, or hidden data access.
Install this if you want the agent to slow down and clarify ambiguous development requests before coding. Expect more confirmation questions, especially because the trigger is broad and the instructions are written in Chinese.
The description and operating instructions are entirely in Chinese, which can effectively force a specific language experience if used in a broader multilingual environment. The file does not indicate that Chinese is optional, user-selected, or required for a documented region-specific purpose.
The activation condition triggers on very broad categories like development, modification, analysis, or design requests, which can cause the skill to activate on a large share of normal user prompts without clear scoping rules. In an agent environment, overly broad auto-activation can unintentionally override or interfere with more appropriate skills, increasing the chance of prompt-routing errors, unnecessary clarification loops, or denial of intended workflow.
No suspicious patterns detected.
