Provide health information, symptom guidance, and wellness support with appropriate medical boundaries.
Security Analysis
high confidenceThis is an instruction-only medical-advice helper whose declared purpose matches its instructions and it requests no extra access, installs, or credentials.
The name/description (medical information, symptom guidance) align with the SKILL.md content. The skill does not request unrelated binaries, environment variables, or configuration paths—everything required is consistent with providing general health information.
The SKILL.md contains runtime instructions and rules that stay within medical information and triage boundaries (emergency recognition, recommend seeing a clinician, no prescriptions). It does not instruct the agent to read files, access system state, call external endpoints, or exfiltrate data.
No install spec and no code files are present (instruction-only). This minimizes disk writes and execution of external code; the install surface is minimal and appropriate.
Requires no environment variables, credentials, or config paths. There are no disproportionate secret or credential requests for the stated purpose.
always:false and no special privileges are requested. The skill is allowed to be invoked autonomously by the agent by default (platform default), which is normal but means it could be used without explicit user prompt if agent policies allow — this is not itself a red flag but users should be aware for medical content.
Guidance
This skill is internally consistent and lightweight — it doesn't install software or request secrets. However: do not treat its output as a clinical diagnosis; always require human clinician review for decisions, prescriptions, or emergency triage. Monitor outputs for hallucinations or incorrect clinical recommendations. Avoid granting the skill access to users' private medical records or to automated actions (e.g., booking appointments or sending messages) without additional safeguards and human review. If you plan to deploy it where users rely on it for care, add explicit disclaimers and logging, and consider restricting autonomous invocation so a human reviews suggestions before any action is taken.
Latest Release
v1.0.0
Initial release
More by @ivangdavila
Published by @ivangdavila on ClawHub
