Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language ADHD education and support skill with no executable code, persistence, or hidden data access, though users should treat its health guidance as informational.
Installers should understand this as an informational ADHD support skill, not a medical provider. Use clinicians for diagnosis, medication, crisis care, and hormone or fNIRS decisions, and avoid entering identifiable child, family, or medical records unless the AI service's privacy handling is acceptable.
The skill strongly constrains output style and audience to Chinese-speaking users without offering any language fallback or explicit locale gating. This can cause unsafe or unusable behavior for non-Chinese users in a mental-health-adjacent context, where misunderstanding medical disclaimers, support guidance, or crisis advice could materially increase harm.
The guidance explicitly suggests using AI to assist with parenting but provides no warning about sharing children's personal, behavioral, or health-related information with third-party AI systems. In this context, users may disclose sensitive family data without understanding retention, model training, or privacy risks, creating avoidable exposure of minors' information.
The entire skill content is written exclusively in Chinese and provides no indication that users may choose another language or opt in to this locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified.
This markdown file consists wholly of Chinese-language instructions and explanations, but does not indicate that the user opted into Chinese or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the policy criteria, forcing a specific language without user choice is a natural-language policy violation.
This markdown file uses only Chinese throughout the title, headings, guidance, and quoted closing text. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no language choice or justification is provided.
No suspicious patterns detected.
