red SKILL.md skillA

red from glebis/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add glebis/claude-skills/red@git:20260603.7f34db8

Pins git:20260603.7f34db8 in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

glebis/claude-skills

Path

confide/skills/red/SKILL.md

Versions recorded

1

Latest version

git:20260603.7f34db8, committed Jun 3, 2026

Size

3,552 bytes

Repository stars

410

License

MIT

Residual re-identification RISK CHECK on text you have ALREADY redacted (defensive, dual-use). Use when the user asks to "check residual re-id risk", "red-team my redaction", "what can an attacker still infer", "is this safe to share", or assess "re-identification risk" after anonymizing. Re-runs the CONFIDE detectors on the redacted output to surface surviving identifiers (singling-out), checks multiple files for linkability, and optionally probes a local model for still-inferable attribute…

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

# confide:red — residual re-identification risk check

A **defensive** audit of YOUR OWN already-redacted output. It does not score against
ground truth and is not a benchmark. It surfaces, qualitatively, what an attacker could
**still** do — mapped to GDPR Art-29: **singling-out**, **linkability**, **inference**.

## GUARDRAILS — read before running
- Run **only on the user's own redacted output**. If asked to de-anonymize or re-identify
  third-party / non-consented data, **refuse**.
- Report risk **categories and counts only** — never produce a step-by-step
  re-identification recipe or guess the hidden values.
- **Local attacker by default.** Enable the cloud/LLM inference probe (`--inference`)
  **only** on synthetic or explicitly consented data.
- **Absence of a finding ≠ safety.** A weak local detector/attacker is a FLOOR, not a
  ceiling. Always tell the user **human review is still required**.
- This pairs with **confide:anon** — run `red` *after* redacting, on the redacted file.

## What it checks
1. **Singling-out (deterministic, offline — the load-bearing signal):** re-run
   `detect_regex` (+ `detect_natasha` if available) on the **redacted** text. Anything
…

Read the whole file at its exact version.

How to install

mdr add glebis/claude-skills/red@sha256:4d61c00007a79844

[![mdr](https://markdownregistry.com/badge/art_noe3a4noirnvdnk6.svg)](https://markdownregistry.com/a/art_noe3a4noirnvdnk6)

Versions

The registry has recorded 1 version of this file, committed on Jun 3, 2026.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_noe3a4noirnvdnk6
GET https://markdownregistry.com/api/v1/resolve?ref=glebis/claude-skills/red
GET https://markdownregistry.com/api/v1/blob/4d61c00007a79844d7dd80e3057894f3dc139ff51ece4157901b8bfa83f8630b

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.

More from glebis/claude-skills

Every file in glebis/claude-skills

Other files named red

Browse by kind, by grade A, or by owner.