Health Manager

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned local health-tracking skill, but users should treat the stored health and medication data as sensitive and review the npm-based install before use.

Before installing, make sure you are comfortable storing health and medication records locally, protect generated reports/backups, and review the npm package because the source is unknown. Treat any health analysis as informational rather than medical advice, and be cautious if you later enable third-party health-account integrations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI06: Memory and Context Poisoning
Medium
What this means

Anyone with access to the database, exported files, backups, or reports could see sensitive health and medication information.

Why it was flagged

The skill persistently stores health metrics, medication records, and notes in a local database.

Skill content
SQLite 数据库存储 ... 血压记录表(收缩压、舒张压、心率、时间、备注) ... 用药记录表(药物、剂量、时间) ... 默认位置:`~/.config/health-manager/health.db`
Recommendation

Use it only on trusted devices, protect the database and report files, avoid placing exports in shared folders, and treat imported notes as data rather than instructions.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing and building a Node package can execute dependency or package scripts on the local machine, even though this is expected for a CLI-based skill.

Why it was flagged

The documented setup asks the user to install Node dependencies and run a build step locally.

Skill content
cd ~/.openclaw/workspace/skills/health-manager
npm install
npm run build
Recommendation

Review package.json/package-lock and install only from a trusted copy, especially because the registry source is listed as unknown.

#
ASI03: Identity and Privilege Abuse
Low
What this means

If these integrations are used, the skill could access health data from third-party accounts or services.

Why it was flagged

The broader documentation describes an optional OAuth-based health-data integration, which would involve delegated access to an external health account if enabled.

Skill content
- **Google Fit**: OAuth 认证,数据同步
Recommendation

Only authorize integrations you intend to use, grant the minimum available scope, and verify where imported data is stored before syncing.

#
ASI10: Rogue Agents
Info
What this means

Reminder settings may continue to exist across sessions and can reveal health routines or medication schedules.

Why it was flagged

The skill supports persistent reminder configuration, but the documented commands show user-created reminders and user controls to toggle them.

Skill content
用药提醒配置 ... 血压监测提醒 ... 运动提醒 ... health reminder add medication "08:00" --message "该吃药了" ... health reminder toggle 1
Recommendation

Review active reminders periodically and disable or delete reminders you no longer want.