Medical Advice
v1.0.1提供医疗咨询和就医建议。根据症状、病史等信息分析可能的原因，提供初步判断和建议，包括是否需要就医、挂什么科、可能的检查项目等。支持常见疾病的症状查询、用药指导、健康建议等。集成 PubMed 医学文献搜索和 OpenFDA 药品信息查询，可引用权威来源。
⭐ 0· 186·0 current·0 all-time
by@djttt
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill name/description (medical advice, literature and drug info) matches the included scripts and SKILL.md: two scripts query PubMed and OpenFDA and a demo script formats symptom-based advice. There are no unrelated environment variables, binaries, or external services requested that would be out of scope for this purpose.
Instruction Scope
The SKILL.md instructs the agent to collect potentially sensitive personal health information (symptoms, medical history, contacts). That is expected for a medical triage skill, but it increases privacy risk. The instructions do not direct reading unrelated system files or transmitting data to endpoints other than PubMed/OpenFDA. The skill includes a proper disclaimer advising users to seek professional care.
Install Mechanism
This is instruction+script only with no install spec: no packages are downloaded or extracted. The scripts use only Python stdlib (urllib) to call well-known HTTPS endpoints (eutils.ncbi.nlm.nih.gov and api.fda.gov). No high-risk install behavior detected.
Credentials
The skill requires no environment variables, credentials, or config paths. The network calls are to public NIH and FDA APIs which do not require secrets. Requested data (user symptoms/history) is appropriate to the stated purpose but is sensitive (PHI), so the lack of credential requests is proportionate.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not modify system or other skills. Autonomous invocation is allowed by platform default; combined with this skill's limited footprint this is not an elevated privilege concern by itself.
Assessment
This skill appears to do what it says: query PubMed/OpenFDA and provide symptom-based advice. Before installing, consider privacy: the skill will ask for sensitive health information — avoid sending identifiable data unless you trust the environment and understand how logs are retained. Verify that you are comfortable with the agent making outbound HTTPS requests to public NIH and FDA endpoints. Remember the tool is informational only (has a disclaimer) and should not replace a clinical diagnosis; if you need medical care, consult a licensed professional. If you want extra assurance, review the two query scripts (query_pubmed.py and query_openfda.py) yourself to confirm no unexpected endpoints or data exfiltration, and ensure your deployment environment does not log full user-provided medical data.Like a lobster shell, security has layers — review code before you run it.
latestvk975mqxj0qs1aandbsdqbazjah82xmsw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.