Security audit
Security checks for vulnerabilities and agentic risk
This is a design-oriented Chinese K-12 teacher evaluation skill with sensitive education-data concepts, but its behavior is disclosed, coherent with its purpose, and contains no executable or hidden mechanism.
Install this only if you want a Chinese K-12 education analytics design aid. If adapted into a real system, treat teacher names, student performance data, rankings, exports, and permission changes as sensitive and require school-approved access controls and privacy review.
The manifest description is written entirely in Chinese and presents the skill as a general-purpose teacher evaluation system, but it does not state that the skill is region-specific or provide any language/locale opt-in. Under the policy, forcing a specific language without user choice is a natural-language policy violation.
The manifest describes a system for generating same-grade class comparison charts, teacher teaching-capability evaluation, role-based access to teacher data, and trend tracing based on student performance data. This document instead specifies a separate教材版本→标准知识点 mapping architecture, including curriculum-standard tables, textbook-version tables, school textbook configuration, and cross-version migration logic, which is not mentioned in the declared skill purpose.
The document is written as a general solution but immediately fixes the skill to Chinese primary and secondary textbooks and the 2022 compulsory education curriculum standard. Because the file does not explicitly state that the skill is only for China-specific deployments or offer any locale choice, it imposes a specific locale context in natural language.
The file is written entirely in Chinese and all example labels, chart titles, and narrative output are fixed to Chinese-language strings. Under the policy rule for language/locale, this can be a violation when a skill imposes a specific language without documenting user choice or a justified locale restriction.
This file presents all user-facing policy content in a single language without stating that the skill is intended only for Chinese-speaking users or offering a language choice. Under the stated policy, forcing one language without opt-in can be a natural-language policy violation.
No suspicious patterns detected.
