56 results available

dicom-metadata-extract

nvidia

·

Last changed

Hardened

This skill has been hardened by Chainguard

Last changed

This version passed the hardening gate. Hardening updated the skill content and independently checked the resulting changes. Classified findings before hardening: 5. Classified findings closed: 1. Classified findings remaining: 4. Unclassified scanner findings remaining: 0. Review findings closed: 9. Review findings remaining: 15.

Open before hardening

3

Medium

2

Low

Open after hardening

3

Medium

1

Low

File	Group	Subtype	Severity	Status
tests/test_basic.py	Malicious Code & Command Execution	Dynamic code execution	Medium	Open
BENCHMARK.md	Sensitive Data & Secret Exposure	Agent snooping	Medium	Open
evals/baseline.yaml	Sensitive Data & Secret Exposure	Agent snooping	Medium	Open
scripts/extract_metadata.py	Malicious Code & Command Execution	Dynamic code execution	Low	Open
SKILL.md	Prompt Injection	Indirect prompt injection	Low	Closed

5 findings

SKILL.md

DICOM Metadata Extract

Purpose

Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
Use the wrapper exactly as documented; do not replace the upstream entrypoint with a handwritten implementation.
Manifest I/O: inputs are dicom_path; outputs are metadata_json.

Instructions

Read skill_manifest.yaml.
Run scripts/extract_metadata.py through the documented command below; keep outputs under a caller-provided run directory.
If a host agent exposes run_script, use run_script("scripts/extract_metadata.py", args=[...]); otherwise run the Bash/Python command shown below.
Check the emitted JSON before treating the run as reviewed evidence.

Available Scripts

Script	Purpose	Arguments
`scripts/extract_metadata.py`	Primary entrypoint declared by skill_manifest.yaml.	`PATH_TO_DICOM [--output OUT.json]`

Prerequisites

Runtime requirements: Python packages listed in runtime.side_effects.pip_packages.
Run commands from the repository root unless an existing section below says otherwise.

Limitations

Small PS3.15-inspired standard-tag subset only; not a complete Basic Application Confidentiality Profile implementation.
Private tags not checked
Burnt-in pixel PHI not detected
Multi-frame handling minimal
Not for clinical deployment, regulatory de-identification, autonomous diagnosis, patient-facing use.

Troubleshooting

Error	Cause	Fix
Empty or schema-invalid output	Wrong input path, unsupported modality, or upstream failure.	Re-run with a known fixture and inspect the wrapper JSON plus stderr.
Validation gate failure	Output violated a declared engineering invariant.	use the gate message to repair inputs.

Reads one DICOM file with pydicom and emits JSON on stdout.


python scripts/extract_metadata.py PATH_TO_DICOM

Output includes transfer_syntax, modality, grouped study/series/image metadata, phi_present, and phi_tags_found.

Use this as the smallest end-to-end example of a Medical AI Skills skill. Do not use it for anonymization, private-tag review, pixel PHI detection, or clinical interpretation.

Install

Install with chainctl


chainctl skill install public/nvidia/dicom-metadata-extract:latest

Get started with chainctl

View source

Harden your own skills

Bring Chainguard's hardening pipeline to your first-party skills — custom rulesets, automated remediation, full audit trail.

Provenance

Upstream sourcehttps://github.com/nvidia/skills

Upstream commit2cd3507404ddb4c833e26fde979f1b0c20c4980d

OCI reference

skills.cgr.dev/public/github.com/nvidia/skills/dicom-metadata-extract:latest

License

Apache-2.0

Files

AGENTS.md

BENCHMARK.md

HARDENING.md

SKILL.md

evals/baseline.yaml

evals/evals.json

fixtures/generate_sample.py

scripts/extract_metadata.py

skill-card.md

skill.oms.sig

skill_manifest.yaml

tests/test_basic.py

validators/output_schema.json

The trusted source for open source

Talk to an expert

Privacy

Terms

© 2026 Chainguard, Inc. All Rights Reserved.
Chainguard® and the Chainguard logo are registered trademarks of Chainguard, Inc. in the United States and/or other countries.
The other respective trademarks mentioned on this page are owned by the respective companies and use of them does not imply any affiliation or endorsement.