medical-qa

医疗健康知识问答技能。用于帮助用户理解症状含义、解读检查报告结果、了解用药常识、提供何时就医的专业建议。当用户询问健康症状、药品说明、检查报告解读、就医建议等问题时触发此技能。

Security Scan

The skill's code and instructions match its stated medical Q&A purpose, but it transmits users' medical queries to an external third‑party endpoint (yunzhisheng) which raises privacy and data‑handling concerns you should consider before installing.

Purpose & Capability

Name/description promise a medical Q&A helper and the code + SKILL.md implement exactly that by calling a remote medical knowledge API (yunzhisheng). There are no unrelated binaries, credentials, or installs requested.

Instruction Scope

Runtime instructions and the provided script only perform HTTP POSTs of the user's query to the cloud service and return the answer. They do not read local files or environment variables. However, the skill will transmit potentially sensitive medical questions to a third party; SKILL.md does mention use of a cloud service but does not describe data retention, logging, or privacy handling.

Install Mechanism

Instruction-only with a small helper script; there is no install spec or downloads. Nothing is written to disk beyond the included script.

Credentials

No credentials or environment variables are requested (proportionate). But the skill sends sensitive user data to an external endpoint without requiring any auth or documenting privacy/retention — this is a privacy concern rather than a credential mismatch.

Persistence & Privilege

Skill does not request always:true, does not modify other skills, and does not persist credentials. Autonomous invocation is allowed (platform default) but not combined with elevated privileges here.

Assessment

This skill behaves as advertised (it posts user questions to a Yunzhisheng medical Q&A service and returns the answer), so the main risk is privacy: your medical questions are sent to an external server. Before installing, verify the third party (shangbao.yunzhisheng.cn) and its privacy/retention policy, avoid sending personally identifying information or detailed medical records through the skill, consider asking users for consent, and test with non-sensitive queries first. If you require stricter data controls, prefer a skill that runs locally or one that documents and authorizes where and how PHI is stored and protected.

医疗健康知识问答

本技能面向有健康自查需求的患者，帮助用户：

• 理解症状含义和可能的原因
• 解读检查报告结果
• 了解用药常识
• 给出何时就医的专业建议

回答原则

1. 温暖共情：使用亲切、口语化的语言风格，提供温暖的健康问答体验
2. 专业可靠：基于权威医学知识库提供准确信息，确保答案的专业性
3. 安全边界：
   • 视情况主动引导用户就医
   • 不提供处方建议
   • 明确告知用户不能替代专业医疗诊断
4. 主动关怀：主动提醒用户关注病情变化，必要时建议及时就医

使用方式

脚本导入

本技能提供自定义脚本，位于 scripts/medical_qa.py。

使用示例

获取完整回答

from scripts.medical_qa import get_answer # 注意导入medical-qa skill中的脚本文件时要根据实际情况注意系统路径问题

# 提问
query = "感冒了要不要吃抗生素（消炎药）？"
answer = get_answer(query)
print(answer)

函数说明

get_answer(query)

通过医疗知识库 API 获取问题的答案。

参数：

• query (str): 用户输入的医疗问题

返回：

• str: 答案文本。如果请求云知声医疗问答服务3次均失败，返回 None

实现细节：

• 向云知声医疗问答服务发送 POST 请求
• 最多发起请求 3 次
• 每次请求超时时间为 600 秒

适用场景

• 用户询问某种症状可能的原因
• 用户希望了解检查报告中的指标含义
• 用户想了解某种药品的用法和注意事项
• 用户想知道是否需要去医院就诊

注意事项

1. 始终提醒用户本回答不能替代专业医生的诊断
2. 对于疑似严重疾病的症状，强烈建议用户及时就医
3. 不提供具体药品处方或剂量建议
4. 保持回答的专业性和准确性，引用权威医学来源