auditing-deid-leakage
Adversarially scan already-de-identified clinical text for residual identifiers and emit a leakage report that blocks release on any hit. Use after OpenMed de-identification when the user asks to verify a redaction, prove no PHI/PII leaked, gate a dataset before sharing, or run a second-pass detector. Covers format and checksum detectors (SSN, Luhn for card numbers, MRN/account patterns, emails, phones, dates), entropy heuristics for high-randomness tokens, severity scoring, and a hard block-on-leak rule. This is the verification half of OpenMed's leakage-first ethos. Hand-off: re-run openmed.
npx skills add maziyarpanahi/openmed --skill auditing-deid-leakage --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Auditing de-id leakage De-identification is **verified, not assumed**. A model-driven redaction can miss a structured identifier (an SSN typo'd with spaces, an account number in a footer, a date in an odd format) — and a single residual identifier defeats the whole release. This skill is the adversarial second pass: scan the *output* of de-identification for anything that still looks like an identifier, score it, and **block release on any leak**. It is the verification half of OpenMed's leakage-first ethos — gate on leakage, not on F1. ## When to use - Right after `deidentifying-clinical-text`, before the de-identified text leaves a trust boundary (export, share, train, publish). - When the user wants proof that "no PHI leaked," a release gate, or a CI check that fails the build if any identifier survives. - As a belt-and-suspenders detector independent of the model that produced the redaction — a deterministic checker catches different failures than the NER. Run this on the **de-identified** text, not the original. The original is expected to be full of identifiers. ## Quick start Two complementary passes — a deterministic structural scan plus a model second-pass diff: ```pytho
- When to use
- Quick start
- Workflow
- Hand-off to / from OpenMed
- Edge cases & gotchas
- Standards & references
What does the auditing-deid-leakage skill do?
Adversarially scan already-de-identified clinical text for residual identifiers and emit a leakage report that blocks release on any hit. Use after OpenMed de-identification when the user asks to verify a redaction, prove no PHI/PII leaked, gate a dataset before sharing, or run a second-pass detector. Covers format and checksum detectors (SSN, Luhn for card numbers, MRN/account patterns, emails, phones, dates), entropy heuristics for high-randomness tokens, severity scoring, and a hard block-on-leak rule. This is the verification half of OpenMed's leakage-first ethos. Hand-off: re-run openmed.
How do I install it?
Run `npx skills add maziyarpanahi/openmed --skill auditing-deid-leakage --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From maziyarpanahi/openmed, a repository with 4,851 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.