Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-design guidance skill with no bundled code, network behavior, credential handling, or hidden persistence; its main risks are usability and write-scope clarity.
Before installing, confirm you are comfortable with a Chinese-first prompt-design guide and use it only when intentionally creating or improving prompts, skills, or agent orchestration. When it generates files, review the draft and destination path before permitting any write or overwrite.
The skill content is written primarily in Chinese and effectively prescribes Chinese-language prompt structures without stating that language should follow user preference. In a prompt-design skill, this can cause unintended language switching, reduce user comprehension, and propagate inaccessible or incorrect prompts into downstream agent workflows.
The trigger guidance uses broad phrases like creating skills, optimizing prompts, designing agents, or orchestration, which are common requests and can cause the skill to activate in situations where the user did not intend it. Over-broad auto-loading increases the chance of incorrect routing, prompt interference, and unintended application of this skill's rules to unrelated tasks.
The workflow says the final SKILL.md is written to disk as a completion condition, but it does not require explicit user consent before modifying files. In agent environments, undocumented write behavior can surprise users and lead to unintended local changes or overwriting artifacts.
No suspicious patterns detected.
