Security audit
Security checks for vulnerabilities and agentic risk
This is a read-only Chinese code-analysis skill that searches user-specified code and does not show hidden execution, persistence, exfiltration, or destructive behavior.
Install this if you want a Chinese-language helper for read-only method analysis. Be aware that implicit invocation is enabled, so the agent may choose it for code-analysis requests; review results before sharing them because they may summarize local proprietary code.
The instruction "使用中文" mandates a specific language for all outputs, but the file does not offer the user a language choice or make this an opt-in preference. This matches the language/locale policy violation category because it imposes a locale/language constraint unconditionally.
The skill enables implicit invocation while exposing a very broad natural-language prompt, which can cause the agent to trigger this skill without an explicit user opt-in or a narrowly scoped activation pattern. In a code-analysis skill, that increases the chance of unintended repository inspection, disclosure of code structure, or surprise tool behavior when a user says something vaguely related to analysis.
The display name, description, and default prompt are entirely in Chinese, which implies a fixed language choice in user-facing skill text. There is no indication that users can opt into another language or that the language restriction is intentionally justified for a region-specific use case.
