Reviewing Reidentification Risk

What it does

When your agent uses it

• The user needs HIPAA Expert Determination (45 CFR 164.514(b)
• Asks whether a dataset is safe to release
• Worries about singling-out via age/ZIP/dates
• Wants a statistical very small risk determination

Example prompts

• “very small risk”
• “/reviewing-reidentification-risk”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Enumerate quasi-identifiers (QIs). List every field an outsider could
2. 2Compute k-anonymity. For each equivalence class (records sharing the same
3. 3Check l-diversity on sensitive attributes. k-anonymity hides which
4. 4Run the empirical attack. run_reid_attack / run_reid_benchmark model an
5. 5Generalize or suppress, then re-score. For singletons / low-k classes,
6. 6Write the determination memo. Record the QIs considered, methods applied,

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • hhs.gov
  • dataprivacylab.org
  • dl.acm.org
  • csrc.nist.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Reviewing Reidentification Risk loads about 1.9k tokens when it runs. Until then it costs about 186 tokens; SKILL.md has 683 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~186

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 683 words, ~1,910 tokens.

name

reviewing-reidentification-risk

description

Run expert-determination-style quasi-identifier risk scoring (k-anonymity, l-diversity) plus OpenMed's empirical re-identification attack on a de-identified dataset, then document residual risk in a defensible memo. Use when the user needs HIPAA Expert Determination (45 CFR 164.514(b)(1)) support, asks whether a dataset is safe to release, worries about singling-out via age/ZIP/dates, or wants a statistical "very small risk" determination. Covers identifying quasi-identifiers, computing k-anonymity / l-diversity, running openmed.eval.attacks.reid (run_reid_attack / run_reid_benchmark) as the adversarial attack, and writing the risk memo. Pairs after deidentifying-clinical-text and auditing-deid-leakage.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

de-identification

metadata.pairs

after

metadata.version

1.0

from openmed.eval.attacks.reid import run_reid_attack, run_reid_benchmark

# Synthetic de-identified records; each row is the released, de-id'd data.
deidentified = [
    {"record_id": "r1", "text": "[NAME], 47F, ZIP 021xx, admitted 2024-03."},
    {"record_id": "r2", "text": "[NAME], 47F, ZIP 021xx, admitted 2024-03."},
    {"record_id": "r3", "text": "[NAME], 88M, ZIP 597xx, admitted 2024-03."},  # singleton
]
# Auxiliary = what an attacker might already hold (e.g. a voter list).
auxiliary = [{"record_id": "v9", "text": "88M ZIP 597xx"}]

result = run_reid_attack(
    fixtures=[],                          # bring your own records below
    deidentified_records=deidentified,
    auxiliary_records=auxiliary,
)
metric = result.to_metric()
print(metric["aux_linkage_rate"],        # empirical linkage success
      metric["k_min"],                   # smallest equivalence-class size
      metric["singleton_count"],         # k=1 records (uniquely identifiable)
      metric["quasi_identifier_count"])

report = run_reid_benchmark(
    suite="golden",
    deidentified_records=deidentified,
    auxiliary_records=auxiliary,
    output_markdown="reid_risk.md",
)

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/reviewing-reidentification-risk of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c