Ai Doctor

AI medical consultation assistant that helps users understand symptoms, conditions, medications, lab results, and treatment options. Provides evidence-based...

Security Scan

The skill's instructions, requirements, and behavior are coherent with an AI medical-consultation assistant and it does not request extra system access or credentials, but provenance is unknown and medical/privacy/legal risks remain.

Purpose & Capability

Name, description, and runtime instructions align: the SKILL.md describes asking clarifying questions, explaining symptoms/conditions/treatments, and giving disclaimers. There are no unrelated environment variables, binaries, or config paths requested that would be inconsistent with a medical advice assistant.

Instruction Scope

The instructions stay within the stated medical-advice scope and do not direct the agent to read files, access system credentials, or send data to external endpoints. However, the skill will handle sensitive personal health information (PHI); SKILL.md does not mention retention, logging, or data handling policies — implementers should ensure conversations with PHI are protected and not leaked or stored inappropriately.

Install Mechanism

No install spec and no code files — instruction-only skill. This minimizes filesystem/remote-code risk because nothing is downloaded or installed.

Credentials

The skill declares no required environment variables, credentials, or config paths. This is proportionate to an instruction-only medical help skill.

Persistence & Privilege

always:false (default) and the skill may be invoked autonomously (platform default). Autonomous invocation is expected, but for medical guidance you should consider requiring human review or limits on autonomous actions and ensure logs and outputs are handled according to privacy/regulatory needs.

Assessment

This skill is internally consistent and doesn't ask for credentials or install code, but because it handles sensitive health information you should: (1) confirm who operates/published the skill (source/homepage unknown) and assess trust; (2) test with non-sensitive queries first; (3) require the agent to always present the written disclaimer and, where possible, cite sources for medical claims; (4) enforce privacy controls — ensure conversations are not logged or retained in a way that would disclose PHI and verify compliance with applicable laws (e.g., HIPAA) if you plan to use it with real patient data; (5) consider a human-in-the-loop or denial policy for high-risk recommendations (emergency triage, prescriptions); and (6) monitor outputs for clinical accuracy before relying on them for decisions.

Provide intelligent, evidence-based medical information to help users understand their health concerns. Explain symptoms, conditions, treatments, medications, and lab results in clear language — always with appropriate disclaimers and guidance on when to seek professional care.

When to Use

• User describes symptoms and wants to understand possible causes
• User asks about a medical condition, diagnosis, or treatment
• User wants to understand their lab results or medical report
• User asks about medications, dosages, or side effects
• User wants to know if they should see a doctor
• User asks "what does my doctor mean by..."

How to Use

1. Listen carefully to the health concern or question
2. Ask clarifying questions: symptom duration, severity, location, associated factors
3. Provide evidence-based information on possible conditions (never a definitive diagnosis)
4. Explain relevant anatomy, physiology, or medical concepts in plain language
5. Give clear guidance: "See a doctor immediately" / "Monitor for X days" / "Can manage at home if..."
6. Always include: "This is health information, not a medical diagnosis. Consult a licensed physician for personal medical advice."

Examples

• "I have a sharp pain in my lower right abdomen, what could it be?"
• "My doctor says I have Type 2 diabetes, what does that mean for me?"
• "Is it safe to take ibuprofen every day for chronic pain?"
• "My ferritin level is 8, is that concerning?"