Clinico Geral

v1.0.20

Use esta skill para perguntas sobre saúde humana, sintomas, doenças, medicamentos, exames, prevenção, primeiros socorros e emergências médicas. Inclui dor, f...

0· 417·1 current·1 all-time
byEdson Cavalca Jr.@edsoneras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (general clinical advice) align with the SKILL.md. The skill requests no binaries, env vars, or config paths — appropriate for an instruction-only conversational medical helper.
Instruction Scope
Instructions are narrowly scoped to providing educational medical information, structured replies, and mandatory disclaimers. One notable non-security concern: the SKILL.md instructs the assistant to avoid saying phrases like 'não sou médico' and to not discuss internal policy or technical limitations, which reduces transparency about model limits; otherwise it does not request files, system state, or external endpoints.
Install Mechanism
No install spec (instruction-only). Nothing is written to disk and there are no external URLs or packages — minimal installation surface.
Credentials
No environment variables, credentials, or config paths are required. The skill does not request access to unrelated services or secrets.
Persistence & Privilege
always:false (not force-included). disable-model-invocation is default false (agent may invoke autonomously), which is normal; the skill does not request elevated or persistent system privileges.
Assessment
This skill is coherent with its stated purpose: an instruction-only medical information assistant in Brazilian Portuguese with required disclaimers. Before installing: 1) Understand it is not a substitute for a real medical consultation — follow the mandated disclaimers and seek care for emergencies. 2) Avoid pasting or sharing sensitive personal health identifiers in chats if you want privacy. 3) Note the skill discourages the assistant from saying "não sou médico" or discussing internal limits; that may make responses sound more authoritative than the underlying model's competence—exercise extra caution for serious concerns. 4) The publisher/homepage is not provided; if you need higher assurance, prefer skills from verified medical organizations or maintainers with a public homepage. 5) Because this is instruction-only and has no code, there is little technical risk, but also no audit trail or references — consider asking the skill to cite sources or recommend verified resources when it gives clinical information.

Like a lobster shell, security has layers — review code before you run it.

latestvk97et199vxv6fyte1rsfxmtc9582486x

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments