Health Guardian
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
Apple Health data may be imported and stored locally from a path the user did not explicitly configure, making sensitive medical readings available to anyone or any agent with access to the skill data folder.
The importer reads health-export files from a hardcoded iCloud container path and persists raw readings into the skill's local data directory. For sensitive health data, this needs clearer user-controlled scoping, retention, and file-protection guidance.
HEALTH_EXPORT_PATH = os.path.expanduser("~/Library/Mobile Documents/iCloud~com~ifunography~HealthExport/Documents")
SKILL_DATA_PATH = Path(__file__).parent.parent / "data"
...
existing["readings"].append(r)Verify the exact source path and data directory before running the importer or cron job. Prefer code that honors config.json, restrict file permissions on the data folder, and define retention/deletion rules for stored health data.
A user may believe no cloud service is involved, while their health data is actually being synchronized through iCloud/Health Auto Export as part of the documented workflow.
The setup explicitly relies on iCloud Drive sync, but the privacy section broadly says 'No cloud.' Even if the skill itself makes no network calls, this wording under-discloses the third-party cloud data flow.
Configure: JSON format, iCloud Drive sync, hourly export ... **Privacy:** Nothing leaves your machine. No cloud. No telemetry.
Treat iCloud and Health Auto Export as part of the data flow. Review their privacy settings and update the skill documentation to distinguish 'the scripts do not send telemetry' from 'the source data may be synced through iCloud.'
If enabled, the agent will continue checking health data on a schedule and may act on alerts until the cron entry is removed.
The skill documents an hourly scheduled task for ongoing health import and anomaly checks. This is disclosed and purpose-aligned, but it creates persistent background monitoring.
Add to your agent's cron (hourly): ... "Run health import and check for anomalies"
Only add the cron job if continuous monitoring is desired, document how to disable it, and periodically review thresholds, alert destinations, and stored data.