ehr-data-parsing

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected data processing tasks for clinical informatics. It utilizes well-known libraries such as python-hl7 and fhir.resources to handle domain-specific data formats.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file path access, or unauthorized network operations. The file read operation open(filepath, "r") is used within a legitimate context for processing local data files as requested by a user.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data (HL7 and FHIR formats). However, the capability inventory is limited to data parsing and transformation into DataFrames. It does not utilize high-risk tools like shell execution, dynamic code evaluation, or network requests that could be exploited via injection. Resource validation is performed using the fhir.resources model validation library.
  • [EXTERNAL_DOWNLOADS]: Dependencies listed (python-hl7, fhir.resources, pandas) are standard packages from the official Python Package Index (PyPI). Documentation links point to legitimate technical references such as HL7.org and ReadTheDocs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 05:59 PM
Security Audit — agent-trust-hub — ehr-data-parsing