Security audit
Security checks for vulnerabilities and agentic risk
This is a locally simulated Chinese-language doctor-matching skill with visible medical triage limits and no evidence of hidden data access, persistence, or remote execution.
Install only if you want a Chinese/Beijing-style mock healthcare matching workflow. Treat outputs as informational navigation help, not medical advice, diagnosis, or emergency triage; use emergency services for serious symptoms and avoid entering more personal health or location detail than necessary.
The README describes symptom analysis, triage, and hospital/doctor matching for consumer medical use, but it does not warn that the output is not medical advice and should not replace professional diagnosis. In a healthcare context, users may over-trust the tool's recommendations and delay urgent care or choose inappropriate departments or providers, creating real health and safety risk.
The natural-language content of the README is fully Chinese, which can effectively force a specific language on users without explicit opt-in. The file does not indicate that the skill is intentionally region-specific or provide an alternative language option.
Without declared permissions the skill's intent is opaque and cannot be validated.
The skill documentation is entirely written in Chinese and frames the interaction/output expectations in that language, but it does not state that users may choose another language or locale. Under the policy rule, a skill that effectively imposes a language without opt-in can be a natural-language policy violation.
This JSON dataset uses Chinese names, departments, titles, specialties, and fee labels throughout, which imposes a specific language/locale in the skill data. Under the policy, language constraints should either be optional for the user or clearly documented and justified as region-specific.
The JSON content is entirely presented in Chinese, including medical summaries, notes, and simulated booking details, with no indication that language selection is configurable or that the file is intentionally limited to a Chinese-only regional workflow. The policy requires flagging language or locale constraints when they are imposed without user opt-in or clear justification.
This markdown template forces Chinese-language output throughout the skill content, including headings and field labels, with no indication that the user can opt into another language. Under the policy, imposing a specific language without user choice is a natural-language policy violation unless the locale constraint is clearly documented and justified.
This file provides symptom-to-department triage guidance, including escalation rules such as directing breathing difficulty, stroke-like symptoms, and persistent chest pain to emergency care, but it does not warn users that the mapping is only informational and cannot replace professional medical assessment. In a medical-doctor-matcher skill, users may rely on these simplified rules for real health decisions, causing delayed emergency care, mis-triage, or inappropriate self-routing when symptoms are ambiguous or severe.
The file presents all workflow instructions exclusively in Chinese and does not indicate that users may choose another language or locale. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern.
The workflow explicitly requires collection of highly sensitive personal health data and location data, but includes no privacy notice, consent step, data minimization rule, retention limit, or handling restrictions. In a medical-matching context, this is dangerous because users may disclose protected health information under the assumption it is necessary, creating elevated confidentiality, compliance, and misuse risk if the data is stored, logged, or shared.
This code presents its CLI description, risk notes, booking notes, and other user-facing text entirely in Chinese, with no option for users to select another language or locale. The policy for this category flags skills that force a specific language without user opt-in, and that behavior is visible across the script's natural-language strings.
This JSON file contains only Chinese names, cities, districts, and service labels, which implies a fixed language/locale context. Under the policy, locale-specific constraints should be explicitly offered as a user choice or clearly documented as region-specific; this file provides neither.
This JSON file contains natural-language values entirely in Chinese for hospital names, cities, regions, and departments. Because SQP-3 applies to all file types and flags locale policy issues when a specific language is forced without opt-in or clear region-specific justification, the absence of any documented locale scope in the file can be read as a language/locale constraint.
The file is entirely in Chinese and does not state that the guidance is limited to Chinese-speaking users or offer an alternative language path. In a healthcare-routing context, language mismatch can cause users or downstream agents to misunderstand symptom severity or department recommendations, increasing the chance of unsafe triage and delayed care.
No suspicious patterns detected.
