Health Recorts
v1.0.1Interview a user and build a personalized health-record system around their goals, reports, and tracking needs. Use when someone wants to organize their heal...
⭐ 0· 73·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and SKILL.md all describe building a local health-record workspace and the files/layouts and behaviors requested are directly relevant. There are no unrelated credential or binary requirements.
Instruction Scope
Instructions stay within the stated purpose (preserve raw files, create Markdown/JSON/CSV summaries, default to local-only, ask before using external OCR/APIs). One operational caveat: the guidance relies on the agent having a meaningful 'local' filesystem and the ability to copy files — if the agent runs in a hosted/cloud environment, the 'local-only' default may not provide the privacy guarantees the user expects. The SKILL.md does not instruct reading unrelated system files or environment variables.
Install Mechanism
No install spec and no code files are included (instruction-only). This is the lowest-risk install profile; nothing will be written to disk by an installer from external URLs.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. Requested access is proportional to the task (manipulating user-supplied health files).
Persistence & Privilege
always is false (not force-included). disable-model-invocation is default (agent may invoke autonomously, which is normal). The skill does not request persistent system-wide privileges or modify other skills' configs.
Assessment
This skill is coherent and low-friction, but it handles sensitive health data—before installing, confirm: (1) where the agent actually stores files (local disk vs hosted/cloud) and whether that matches your privacy needs; (2) that the agent runtime will not automatically upload or back up the health/ folder to third-party services; (3) you will explicitly approve any external OCR or cloud-processing on a per-case basis as the SKILL.md recommends; (4) the agent has permission only to touch intended files (avoid running this skill in an environment that already has broad access to other personal data); and (5) monitor future updates to the skill for added code or network behaviors. Note: the skill's name has a minor typo ('Health Recorts') — that alone is not harmful but may indicate an unpolished package.Like a lobster shell, security has layers — review code before you run it.
latestvk97c6xs1dya626a2xa4xh48cfs83kwbt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.