hipaa-compliance-checker
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains installation instructions referencing the author's official GitHub repository (
Open-Medica/open-medical-skills) via the commandnpx skills add. This represents a standard deployment mechanism for the vendor's resources. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as its primary purpose is to ingest and process untrusted clinical data.
- Ingestion points: Individual clinical notes or document collections (described in SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing examples.
- Capability inventory: Performs entity extraction, masking, and synthetic data replacement (obfuscation) across clinical text.
- Sanitization: No input sanitization or validation of the clinical text is mentioned before processing.
Audit Metadata