Security audit
Security checks for vulnerabilities and agentic risk
This skill is a text-only coaching aid for assessing a skill level and AI replacement risk, with no code execution, persistence, credential access, or hidden data handling.
Install this if you are comfortable using a Chinese-language skill that asks you to describe a specific ability and recent real projects. Do not include sensitive employer, client, or personal details unless they are necessary for the assessment.
The manifest description is written entirely in Chinese and frames the skill's invocation phrases and purpose only in that language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale limitation is explicitly justified, which is not present here.
The display name and short description are entirely in Chinese, while the file does not indicate that language selection is optional or that the skill is intended only for a Chinese-language audience. This can violate language/locale policy expectations when a skill imposes a specific language without user opt-in.
The default prompt is a broad, natural-language request that can be triggered in ordinary conversation without strong invocation boundaries. In agent systems that auto-route or infer tool/skill use from user phrasing, this can cause unintended activation, privacy leakage through over-broad context use, or misuse of the skill outside the user's explicit intent.
The file presents all instructional content in Chinese and does not indicate that language selection is optional or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
