scrub-pii-from-text SKILL.md skillA
scrub-pii-from-text from contextjet-ai/awesome-llm-observability is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add contextjet-ai/awesome-llm-observability/scrub-pii-from-text@git:20261015.76d5de4Pins git:20261015.76d5de4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- contextjet-ai/awesome-llm-observability
- Path
skills/scrub-pii-from-text/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261015.76d5de4, committed Oct 15, 2026
- First version recorded
- Jul 5, 2026
- Size
- 2,194 bytes
- Repository stars
- 45
- License
- a license file GitHub does not identify
Use this to strip PII (emails, credit cards, SSNs, phone numbers, IPs, IBANs) out of text before it is logged to a tracing backend or sent to a third-party model. Trigger on "redact PII", "scrub sensitive data", "mask PII before logging", "don't send customer data to the tracing tool", especially for finance/healthcare/regulated apps. Ships a runnable, tested scrubber with a Luhn check to cut false positives.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Scrub PII from text
Observability captures prompts and completions, which in a regulated app can mean shipping account numbers or PII to a third-party backend. This skill ships a scrubber you can run in the export path so raw values never leave your process.
## Use the bundled script
[`scripts/pii_scrub.py`](scripts/pii_scrub.py) is pure Python, no install needed:
```python
from pii_scrub import scrub, find_pii
scrub("email a@b.com, card 4111 1111 1111 1111") # -> "email <email>, card <card>"
find_pii(text) # [("email", "a@b.com"), ("card", ...)]
```
It masks emails, credit cards (**Luhn-validated**, so random 16-digit order ids are not flagged), US SSNs, phone numbers, IPv4 addresses, and IBANs. Run it directly: `python scripts/pii_scrub.py`.
## How to apply it
1. **Redact before export**, not after: call `scrub()` in your span processor / logging hook so no path bypasses it (see `redact-pii-for-tracing` for where that hook goes).
2. **Redact both directions:** user input and model output (models echo PII back).
…Read the whole file at its exact version.
How to install
mdr add contextjet-ai/awesome-llm-observability/scrub-pii-from-text@sha256:fdc8c7b7c55d3dccThe line at the top of this page pins the label git:20261015.76d5de4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2pwhu46g4vnpfrec)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 5, 2026 and Oct 15, 2026, about one every 102 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.76d5de4 latest | 2026-10-15 | 76d5de4 | 2,194 B | A | view · diff |
| git:20260705.4a31848 | 2026-07-05 | 4a31848 | 2,207 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2194 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
contextjet-ai/awesome-llm-observability · 45 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2pwhu46g4vnpfrec GET https://markdownregistry.com/api/v1/resolve?ref=contextjet-ai/awesome-llm-observability/scrub-pii-from-text GET https://markdownregistry.com/api/v1/blob/fdc8c7b7c55d3dccf0c4f5eb2ee9e78a429d372145badd5bb4fda10f343bf0a2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.