Menu

Individual skill

phi-prompt-guard

0upvotes

Runtime, prompt-time behavioral guardrail that helps reduce PHI exposure in LLM-assisted workflows by detecting PHI-bearing prompts, avoiding unsafe tool actions that would pull more PHI in, and redirecting users toward de-identified or synthetic inputs. Use when the user is about to paste, query, or read clinical/patient data, or when an action (DB query, file read, tool output) may pull PHI into the conversation. Honors a [PHI-OK] attestation for synthetic / test data.

scientific-skills/Other/phi-prompt-guard/SKILL.md

Read pinned source

Source commit 686e09dfdb45d9fa1a08664f06bb93769b3c9d91

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
2,048
Repository last updated
Sep 17, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
> **Contributed by**: [@ndu-bioinfo](https://github.com/ndu-bioinfo)

# PHI Prompt Guard

A behavioral skill that instructs the agent to refuse, redact, or redirect when the live prompt — or an action the agent is about to take — would push more Protected Health Information (PHI) into the LLM context window. Because this is a pure in-context behavioral skill with no pre-submit filter or middleware, it cannot literally prevent PHI that a user has already pasted from reaching the model; what it can do is reduce further PHI propagation after detection, avoid agent-initiated actions that would pull additional PHI in, and steer the user toward de-identified or synthetic inputs.

Intended for contexts where the model provider has **not** been approved to receive PHI under a Business Associate Agreement (BAA) or equivalent organizational authorization — any data placed in the prompt is sent to a third-party API outside the organization's control and may be cached or logged depending on vendor terms.

## When to Use

- The user pastes (or is about to paste) clinical, patient, or specimen data into the conversation.
- The agent is about to run a database client (`psql`, `mysql`, `mongo`, `duckdb`, `sqlite3`, `bq`, `snowsql`, `redis-cli`, `clickhouse-client`, `cqlsh`) or a dump tool (`pg_dump`, `mysqldump`, `mongodump`) against an environment that may contain PHI.
- The agent is about to read a file whose contents may contain identifiers (lab reports, EHR exports, accession-keyed CSVs).
- The user pastes a **clinical document by type** — H&P, SOAP note, discharge summary, progress note, op note, path report, radiology report, HL7 v2 message, FHIR resource JSON, CCD/CDA — these are PHI-by-construction even when no trigger keyword is present.
Back to top