Clinical Anonymization
Anonymizes clinical text by removing or replacing personally identifiable information (PHI/PII) such as names, dates, locations, identifiers, and contact details. Use when processing clinical notes, patient records, or any sensitive healthcare data.
Install
$ agentstack add skill-elisaterumi-ai-clinical-agent-skills-anonymization ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-elisaterumi-ai-clinical-agent-skills-anonymization) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
When anonymizing clinical text, follow these steps:
1. Identify sensitive information
Detect and classify all Personally Identifiable Information (PII/PHI), including:
- Names (patients, doctors, relatives)
- Dates (birth, admission, discharge, events)
- Locations (cities, hospitals, addresses)
- Identification numbers (CPF, RG, SSN, medical record numbers)
- Contact information (phone numbers, emails)
- Organization names (clinics, hospitals, employers)
- Geographic details smaller than a state level
- Any unique identifiers that can re-identify a person
2. Apply anonymization
Replace each entity with a consistent placeholder:
- [PATIENT1], [DOCTOR1]
- [DATE_1]
- [LOCATION_1]
- [ID_1]
- [CONTACT_1]
- [ORG_1]
Rules:
- Maintain consistency: the same entity must always map to the same placeholder
- Do not invent or infer missing data
- Do not remove clinical meaning
- Use consistent indexed placeholders per entity type. If multiple entities of the same type exist, assign incremental IDs (e.g., [PATIENT1], [PATIENT2]).
3. Preserve clinical utility
- Keep all medical information intact:
- symptoms
- diagnoses
- medications
- procedures
- Maintain sentence structure and readability
- Avoid over-anonymization that removes useful context
4. Generalization (when needed)
If exact anonymization is not possible, generalize:
- Exact age → age range (e.g., "84 years" → "80+ years")
- Specific date → month/year or relative time ("March 2023" → "[DATE_1]")
- Precise location → broader region
5. Validate output
Before returning the result:
- Ensure no PII/PHI remains
- Ensure consistency of placeholders
- Ensure medical meaning is preserved
6. Output format
Return only the anonymized text.
Do not include explanations. Do not include metadata unless explicitly requested.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: elisaterumi-ai
- Source: elisaterumi-ai/clinical-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.