All skills
nvidia avatar

/dicom-metadata-extract

@2cd3507
by NVIDIA Corporationnvidia/skills3.5k stars
424

Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.

Use this Skill: https://skilld.dev/gh/nvidia/skills/dicom-metadata-extract

This session only. Nothing lands on disk.

AGENTS.md

≈127 tokens on demand. Your agent reads this file only when SKILL.md points to it.

dicom_metadata_extract - Agent Guide

Smallest end-to-end skill. Use it as the layout template.

Rules:

  • Keep output fields aligned with validators/output_schema.json.
  • Extract only literal DICOM header values.
  • Do not infer modality, body part, diagnosis, or clinical meaning.
  • Keep the invalid-input example reachable from examples/.

Run:

make run-skill SKILL=dicom_metadata_extract \
  FIXTURE=skills/dicom-metadata-extract/fixtures/sample_ct.dcm \
  OUT=runs/dicom_metadata_demo

Source: SKILL.md on GitHub

No alerts16d3 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill is a metadata extraction tool for DICOM medical imaging files. It allows agents to read headers and check for standard Private Health Information (PHI) tags. No malicious behavior, obfuscation, or unauthorized data exfiltration was detected. The skill includes appropriate disclaimers regarding the scope of its PHI detection capabilities.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

Signed by skilld at 2cd3507. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
What it can do
Runs commands
permissions
[
  "file_read",
  "file_write",
  "shell"
]
All 1 allowed tools
Bash
Other metadata
metadata
{
  "author": "NVIDIA MedTech Team",
  "tags": [
    "MedTech",
    "DICOM",
    "metadata"
  ]
}

README badge

README badge for nvidia/skills/dicom-metadata-extract