dicom-series-to-volume

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs local file transformations on DICOM datasets. It uses standard, well-known Python libraries (pydicom, nibabel, numpy) for medical imaging tasks.
  • [SAFE]: Extensive documentation is provided in the SKILL.md and BENCHMARK.md files, clearly outlining the tool's limitations (no multi-frame support, single-series only) and safety warnings regarding clinical use.
  • [SAFE]: The skill includes a 'fixtures' directory and a generation script (generate_fixtures.py) to create synthetic datasets for testing, which is an excellent security and reliability practice to avoid using real Patient Health Information (PHI) during development.
  • [SAFE]: The YAML manifest (skill_manifest.yaml) includes detailed runtime constraints, validation gates (sanity_checks), and reproducibility metrics, which helps ensure the agent operates within a restricted and predictable environment.
  • [SAFE]: The metadata extraction in scripts/series_to_volume.py is limited to standard DICOM header fields (Modality, StudyInstanceUID, etc.) necessary for imaging provenance and does not access sensitive system files or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:42 PM
Security Audit — agent-trust-hub — dicom-series-to-volume