Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed Chinese K-12 math lesson-planning skill that uses limited class learning data with consent controls and no hidden executable behavior.
Use this skill for Chinese-language math lesson planning. Before enabling cross-skill sharing or student writeback, confirm the teacher has the right class workspace and the relevant student/guardian consent; review generated questions and records before saving them.
The manifest explicitly excludes '班级错因统计与干预（转 xiaozhi-teach-math-error-analyzer）'. However, the skill documentation later states it reads classWorkspace.weaknessRank[] to target class weaknesses and can send teacher_writeback updates with weakKnowledgePointUpdates[], which is behavior in the area of error analysis/intervention rather than just lesson-plan drafting.
The trigger phrases are very broad and map to common teacher utterances such as '这个概念怎么讲' or '教案怎么写,' which can cause unintended skill activation in ordinary conversations. In a skill that can read class weakness data and prepare student writebacks or cross-skill handoffs, accidental activation increases the chance of unnecessary data exposure, overcollection, or actions being suggested in the wrong context.
The title and all instructional content are written exclusively in Chinese, and the document presents itself as the single authoritative template for concept construction. Because there is no opt-in, language choice, or documented region-specific justification, this creates a natural-language locale policy concern.
This markdown file is natural-language instructional content, and it consistently requires Chinese to use or understand the rubric. Under the policy, forcing a specific language without user opt-in or a clearly documented locale-specific justification is a natural-language policy violation.
Suspicious Unicode normalization or mixed-script content
The manifest says this skill is for preparing math lesson plans, concept-building paths, example sequencing, variant exercises, summaries, and error archives, and explicitly says it does not handle exams/papers. This file instead defines a general 'AI item self-check protocol' for generated questions, including teacher-side labeling before writing into a question bank or exam, which aligns more with assessment/item-generation workflows than lesson-plan authoring.
The description is entirely prescriptive in Chinese and includes localized terminology such as '老师通用' and references to a shared vocabulary, but it does not indicate that language choice is optional or limited to a China-specific deployment context. Under the policy, forcing a specific language/locale without opt-in is a natural-language policy concern.
The skill file is entirely written in Chinese and provides operational guidance only in that language, with no indication that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without user opt-in is reportable unless the locale constraint is explicitly justified.
The entire shared guidance is written only in Chinese and includes user-facing phrasing that presumes Chinese-language interaction, but it does not offer any language choice or document that the skill is intentionally limited to Chinese-language use. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
The document is written entirely in Chinese and states it is the single authoritative vocabulary source for the whole repository, which effectively imposes a specific language/locale on downstream skills. There is no indication of user opt-in, alternative language support, or an explicit justification that the repository is intended to be Chinese-only or region-specific.
The manifest frames the skill as a teacher lesson-planning tool and specifically excludes several adjacent tasks, while the body documents collaboration to parent-communication for '数学进步反馈' and includes a user control '不要给家长看'. Although this is a handoff rather than direct generation, it expands the described behavior into parent-sharing workflow management.
The template title and instructions are entirely in Chinese, and there is no indication that language selection is optional or limited to a justified region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
This markdown file contains user-facing instructions exclusively in Chinese, and there is no indication that users can choose another language 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.
This markdown template appears to require Chinese-language use throughout, and there is no indication that users may choose another language or that the locale restriction is mandatory for a region-specific purpose. That creates a natural-language policy concern under the language/locale rule.
No suspicious patterns detected.
