NYC
skills/ovachiever/droid-tings/pydicom/Gen Agent Trust Hub

pydicom

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): While the skill handles sensitive medical data (DICOM PHI), it does so within the context of its stated purpose. The anonymize_dicom.py script specifically implements security best practices by providing a mechanism to strip PHI from files. No network operations or unauthorized data access patterns were detected.
  • [Indirect Prompt Injection] (SAFE): The skill processes external DICOM data which could contain malicious strings in metadata tags. However, the scripts are used for extraction and transformation; they do not use the content of these tags to generate commands or secondary AI actions, effectively mitigating the risk of indirect injection.
  • [External Downloads] (SAFE): The scripts reference standard Python libraries (pydicom, numpy, pillow). These are common dependencies for medical imaging and are not downloaded dynamically from untrusted sources within the skill code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM