Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only frontend performance audit skill with no executable code, persistence, credential handling, or hidden authority.
Install this if you want a Chinese-language frontend performance audit helper. Non-Chinese users may find the output format and labels less accessible unless they explicitly ask the agent to translate or adapt the report language.
This file uses Chinese throughout the description and operational instructions, which effectively forces a specific language for use of the skill. The policy allows locale constraints only when users are given a choice or when the restriction is clearly documented and justified, neither of which is present here.
The skill metadata hard-codes a Chinese display name and description, which can steer the agent to respond in Chinese even when the user did not request that language. This can reduce user comprehension, create consent and usability issues, and in security-sensitive contexts may obscure important warnings or outputs from users expecting another language.
The entire skill reference and its output rules are written as mandatory Chinese instructions, including prescriptive language such as '必须先写证据，再写推断'. There is no indication that the user may choose another language or that the skill is restricted to a Chinese-specific compliance or regional context.
The file title and instructions are entirely in Chinese and direct the model to always use the specified output structure, implying a Chinese-language response format by default. This can violate language/locale policy if the skill forces a specific language without user opt-in or an explicit justification.
No suspicious patterns detected.
