purview-customer-key

purview-customer-key is a skill for Claude Code, Codex from vinayaklatthe/microsoft-security-skills. It costs 235 tokens per session (2,235 once invoked), scanned A, original, MIT.

Guidance for customer-controlled encryption in Microsoft Purview using Customer Key and Double Key Encryption. These options let an organisation control encryption keys, with Double Key Encryption adding a separate customer-held key for the most sensitive documents.

In plain words
What is it for?
Use it to plan customer-held keys, key revocation for crypto-shredding, and label-based client-side encryption for documents that service-side tools must not read.
Why use it?
Some regulated or sovereignty-sensitive organisations need stronger control over who can decrypt their data. This helps decide when Microsoft-managed encryption is not enough.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan customer-held keys, key revocation for crypto-shredding, and label-based client-side encryption for documents that service-side tools must not read.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinayaklatthe/microsoft-security-skills/purview-customer-key
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vinayaklatthe/microsoft-security-skills --skill purview-customer-key
Clone the repo
git clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for purview-customer-key

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key)
Your own site
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for purview-customer-key

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-customer-key.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 235 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00235 $0.02235
Opus 5 $0.00118 $0.01118
Sonnet 5 $0.00047 $0.00447
Haiku 4.5 $0.00023 $0.00224

Measured 9d ago against content hash 76b01b628bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

purview-customer-key scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/purview-customer-key/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Purview Customer Key & Double Key Encryption

Microsoft already encrypts M365 data at rest with Microsoft-managed keys. These additional controls let regulated or sovereignty-sensitive customers hold the keys themselves:

  • Customer Key — customer-supplied root keys (in Azure Key Vault HSM) wrap service data-encryption keys for Exchange, SharePoint, OneDrive, Teams (chats/files), and Purview. Revoke the key → Microsoft can no longer decrypt → service-data path crypto- shredded.
  • Double Key Encryption (DKE) — sensitivity-label-driven client-side encryption where one key is customer-held in a self-hosted key release service. Microsoft never sees that key; service-side features (search, eDiscovery, Copilot) cannot read the content.

This skill covers both — when to use which, the architectures, and the operational realities.

When to use

  • Regulatory mandate to hold encryption keys (financial sector sovereignty, defense, certain EU public sector).
  • Crypto-shredding requirement (provable destruction by key revocation).
  • The highest-sensitivity documents that must not be readable by Microsoft or by any service-side process even temporarily.

Do not use this skill for Azure resource encryption (azure-key-vault), generic sensitivity-label rollout (purview-information-governance), or GRC frameworks (compliance-manager).

Customer Key vs DKE — pick consciously

Feature Customer Key DKE
Scope All data in selected M365 services Per-document, label-driven
Encryption point Service-side, transparent Client-side, before upload
Microsoft can read for service features? Yes (until key revoked) No
eDiscovery, Search, Copilot, DLP work on content? Yes No
Key custody Azure Key Vault HSM (customer subscription) Customer-hosted key release service (on-prem or your cloud)
Crypto-shred via revocation? Yes (service-wide) Per-document by destroying key
Use case Sovereignty, blanket regulator demand Crown-jewel docs only

Read the full file on GitHub · 169 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 169 lines · 235 tokens per session scan A 76b01b628bbe

Subscribe to this mod's changes

purview-customer-key is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 235 tokens to every session and 2,235 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

rfp-response-compliance-review

Reviews a draft proposal against the firm's configurable compliance rules — prohibited language, required disclosures, role and positioning boundaries, and procurement-submission requirements. Logs all findings to the Review Findings SharePoint list and annotates the draft document for salesperson and reviewer…

pnp/sharepoint-skills · 57 tokens

power-automate

Use when operating Microsoft Power Automate cloud flows from code — create, enable, update, list or delete via the Dataverse Web API (workflow table, category 5) with Entra ID OAuth2, plus run-history debugging. NOT designing the flow definition (that is automation-flows), NOT picking a platform by billing model (that…

ericrisco/rsc-harness · 82 tokens

carta-witness-signatures

Status of witness and spousal-consent signature requests on option grants, RSAs, PIUs — who still needs to sign, and what's awaiting signature, signed, or expired. Covers one award, one company, or a whole portfolio. Read-only.

carta/plugins · 58 tokens

carta-hmrc-limits

Report a UK company's HMRC EMI/CSOP limit usage. Use when asked how much EMI allowance is left, whether the company is near the £6m EMI limit, who is close to or over their £250k individual limit, CSOP headroom, or whether a planned grant fits.

carta/plugins · 68 tokens

carta-interaction-reference-core

The non-negotiable half of Carta's AI agent interaction rules — financial precision, data provenance, the AI-computation gate, how to confirm, and trust & safety. Loaded ONCE per conversation, before any response that presents or writes Carta financial data. Sufficient on its own for write flows; a flow that also…

carta/plugins · 88 tokens

compliance-verifier

Use this agent to validate deployments against GDPR, HIPAA, SOC2, and other regulatory compliance frameworks and generate audit reports.

samibs/skillfoundry · 30 tokens