Security audit
Security checks for vulnerabilities and agentic risk
This is a teacher-facing exam design skill whose data use and regional scope are disclosed and aligned with its purpose.
Install this for Mainland China Chinese K12 teacher exam-design workflows. If used in another region or language, localize curriculum standards, consent/privacy assumptions, and crisis-resource contacts first; teachers should also review AI-generated questions manually before using them in real exams.
This JSON schema is a manifest-type file, so natural-language policy checks apply. The schema uses Chinese-only descriptive text and constrains multiple user-facing values to Chinese terms, but it does not document that the skill is region-specific or provide any language/locale opt-in, which can violate a language-choice policy.
The entire shared skill guidance is written as prescriptive operational policy in Chinese, including required wording and interaction patterns, but it does not indicate that language choice should follow the user's preference or provide any opt-in. This can amount to a language/locale policy violation because it implicitly fixes the skill behavior to a specific language.
The file explicitly sets the default operating context to Mainland China Chinese K12 and says deployments to other regions should not be used directly without prior localization. This is not code execution risk, but it is a real security/safety configuration weakness because it can cause the agent to provide region-inappropriate emergency contacts, legal assumptions, age-of-consent handling, and curriculum guidance when user locale is unknown or different.
This markdown file contains user-facing instructions and templates exclusively in Chinese, beginning with the title at L001 and continuing throughout the document. Under the policy rule for natural-language violations, forcing a specific language without an explicit user choice can be a locale/language policy issue unless clearly justified.
No suspicious patterns detected.
