Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed Chinese-language academic writing diagnostic skill that summarizes six Method-section review dimensions without bundled code, persistence, credential access, or hidden data movement.
Install this if you want a Chinese-language summary workflow for diagnosing psychology Method sections and already have or trust the six named diagnostic sub-skills it depends on. Review the dependency names and note the documentation inconsistency around whether those sub-skills are called.
Referenced artifact was not completely inspected
**配套**：`references/rubric.md`（汇总评分规则）+ 6 个分项 Skill 的 `SKILL.md` + `references/checklist.md` + `references/rubric.md` + `references/examples/positive/`
The manifest description is entirely in Chinese and presents the skill as a Chinese-language writing diagnostic workflow, but the file does not state that language choice is optional or limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
L503-L510 与 L522-L533 明确说明该 skill 会并行调用 6 个分项 skill；但 L512-L514 的标题与内容却写成“下游 Skill（被本 Skill 调用的）无（本 Skill 是诊断链的终点，不调用其他 Skill）”。这不是单纯信息缺失，而是文档对 skill 是否调用其他 skill 给出相反描述，容易误导开发者对实际编排行为的理解。
This markdown rubric is written entirely in Chinese and defines mandatory output/reporting behavior for the skill, but it does not indicate that the language is optional or user-selected. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless the locale restriction is clearly justified.
No suspicious patterns detected.