Enforcing Nophi Logging

What it does

When your agent uses it

• The user wants a Python logging.Filter that redacts protected health information before records are emitted
• Wants to keep PHI out of OpenTelemetry spans
• Needs structured no-PHI log fields
• Is worried that logs and stack traces are leaking patient data

Example prompts

• “scrub logs”
• “redact PHI from logs”
• “no-PHI logging”
• “/enforcing-nophi-logging”

Requirements

• Python 3

Workflow steps

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

1. 1Inventory sinks. List every place a clinical string can reach: app logs,
2. 2Install the regex pre-filter for structured identifiers (SSN, card, email,
3. 3Add the model fallback (openmed.extract_pii) for free-text PHI on the
4. 4Switch to structured fields. Replace "log the text" with "log counts,
5. 5Fail closed. On any scrub error, drop the message content, not the
6. 6Test it. Unit-test that known PHI strings never survive a round trip

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
  • cheatsheetseries.owasp.org
  • opentelemetry.io
  • docs.python.org

  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

Enforcing Nophi Logging loads about 1.9k tokens when it runs. Until then it costs about 157 tokens; SKILL.md has 563 words of instructions outside code blocks.

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

~157

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). 563 words, ~1,900 tokens.

name

enforcing-nophi-logging

description

Add a logging and telemetry guard that scrubs or blocks PHI from logs, traces, and error reports around an OpenMed deployment. Use when the user wants a Python logging.Filter that redacts protected health information before records are emitted, wants to keep PHI out of OpenTelemetry spans or error trackers, needs structured no-PHI log fields, or is worried that logs and stack traces are leaking patient data. Trigger on "scrub logs", "redact PHI from logs", "no-PHI logging", "logging filter", "telemetry redaction", "logs leaking patient data", or "OpenTelemetry redaction" in an OpenMed deployment.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

deployment-ops

metadata.pairs

adjacent

metadata.version

1.0

import logging
import re
import openmed

# Cheap regex pre-filter for the highest-risk structured identifiers. This runs
# on every record, so keep it fast; the model is the fallback for free-text PHI.
_FAST_PATTERNS = [
    (re.compile(r"\b\d{3}-\d{2}-\d{4}\b"), "[SSN]"),
    (re.compile(r"\b\d{16}\b"), "[CARD]"),
    (re.compile(r"\b[\w.+-]+@[\w-]+\.[\w.-]+\b"), "[EMAIL]"),
    (re.compile(r"\b(?:\+?\d[\d().\-\s]{7,}\d)\b"), "[PHONE]"),
]

class NoPHIFilter(logging.Filter):
    """Redact PHI from a log record before it is emitted. Fail closed."""

    def __init__(self, model_name: str | None = None, use_model: bool = True):
        super().__init__()
        self.model_name = model_name
        self.use_model = use_model

    def filter(self, record: logging.LogRecord) -> bool:
        try:
            message = record.getMessage()
            record.msg = self._scrub(message)
            record.args = ()                 # message already rendered & scrubbed
        except Exception:
            # Never let the logger leak on error — drop the message, keep the level.
            record.msg = "[REDACTED: scrub error]"
            record.args = ()
        return True                          # keep the (now-clean) record

    def _scrub(self, text: str) -> str:
        for pattern, tag in _FAST_PATTERNS:
            text = pattern.sub(tag, text)
        if not self.use_model:
            return text
        # Model fallback for free-text PHI (names, locations, dates). Replace by
        # offset, right-to-left, so earlier offsets stay valid.
        spans = openmed.extract_pii(text, model_name=self.model_name) \
            if self.model_name else openmed.extract_pii(text)
        for e in sorted(spans.entities, key=lambda s: s.start, reverse=True):
            text = text[:e.start] + f"[{e.label}]" + text[e.end:]
        return text

# Attach to every handler that might emit clinical text.
handler = logging.StreamHandler()
handler.addFilter(NoPHIFilter(model_name="OpenMed/Privacy-PII-Detection"))
logging.getLogger("openmed.service").addHandler(handler)

logger.info(
    "deidentified note",
    extra={
        "doc_id": doc_id,                       # opaque id, not the text
        "phi_entity_count": len(result.entities),
        "phi_labels": sorted({e.label for e in result.entities}),
        "char_len": len(text),
        # offsets/hashes for debugging; never the plaintext span
        "phi_offsets": [(e.start, e.end) for e in result.entities],
    },
)

© 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/enforcing-nophi-logging of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c