What is purview-ai-hub?

Guidance for Microsoft Purview Data Security Posture Management for AI, formerly called AI Hub. It shows which AI applications people use, what sensitive information enters them, and which policies protect that information.

Use it to discover AI applications, review prompts and responses, restrict sensitive data from unsanctioned tools, and audit AI interactions with approved services.

Employees may use approved and unapproved AI tools without a central view of the data they share. This helps identify risky AI use and apply controls across Microsoft Copilot, agents, and third-party AI services.

purview-ai-hub — Skill for Claude Code and Codex by vinayaklatthe

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-ai-hub

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub)

Your own site

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-ai-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,903 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.

Model	Per session	Once invoked
Fable 5.1	$0.00232	$0.01903
Opus 5	$0.00116	$0.00951
Sonnet 5	$0.00046	$0.00381
Haiku 4.5	$0.00023	$0.00190

Measured 9d ago against content hash 418231ebfcb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

purview-ai-hub 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-ai-hub/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Purview AI Hub (DSPM for AI)

Purview AI Hub — re-cast as Microsoft Purview Data Security Posture Management (DSPM) for AI — is the cross-AI visibility layer: which AI apps are being used, by whom, with what sensitive content, and what policies are protecting that content. It covers Microsoft Copilot products, Copilot Studio agents, and third-party generative AI (ChatGPT, Gemini, Claude, Perplexity, and ~600 catalogued AI apps).

When to use

You need visibility into AI usage across the organization (sanctioned and shadow), with policies that prevent sensitive data leaving for unsanctioned AI and that audit prompts into sanctioned AI.

Do not use this skill for AI workload-side posture (defender-for-cloud-ai), Azure AI Content Safety prompt filtering (azure-ai-content-safety), or the Copilot rollout playbook (copilot-for-m365-readiness).

What you see and control

Surface	Visibility	Policy
Microsoft 365 Copilot	Prompts, responses, sensitivity context	DLP for Copilot, sensitivity-label restrictions
Copilot Studio agents	Agent interactions per user	Same DLP + label model
Third-party AI (ChatGPT, Gemini, etc.)	Discovery via Defender for Cloud Apps + Edge for Business endpoint signals	Browser DLP block/warn; collection of prompt evidence on Edge
Custom AI apps (your own)	Via Purview SDK / Microsoft Graph (preview)	Custom labels and DLP integration

Approach

Prereqs. Defender for Cloud Apps with cloud discovery; Microsoft Edge for Business deployed for the prompt-capture story; Purview E5 / Compliance E5; Audit Premium recommended.
Turn on AI app discovery. AI Hub uses your cloud discovery logs (Defender for Cloud Apps from firewall/proxy/MDE) to populate the catalog. Within 7 days you see what AI apps people are using, by user count and traffic volume.
Categorize the AI app catalog.
- Sanctioned: corporate-approved (Microsoft 365 Copilot, your Copilot Studio agents, paid enterprise ChatGPT/Gemini with DPA).
- Tolerated: not approved but not blocked (yet).
- Unsanctioned/blocked: shadow consumer AI without enterprise terms.

Read the full file on GitHub · 131 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.

9d ago First seen · 131 lines · 232 tokens per session scan A 418231ebfcb9

Subscribe to this mod's changes

purview-ai-hub is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 232 tokens to every session and 1,903 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.

Data and AI Security ai-agents copilot defender entra entra-id microsoft

deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.

davila7/claude-code-templates · 38 tokens

skill-meta-prompt

Craft better prompts using proven optimization techniques — use when your prompt needs refinement.

nyldn/claude-octopus · 19 tokens

dashscope

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.

calesthio/OpenMontage · 93 tokens

session-rag-eval

Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.

chatboxai/chatbox · 25 tokens

microsoft-extensions-ai

Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator…

managedcode/dotnet-skills · 128 tokens

semantic-kernel

Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. USE FOR: adding AI-driven prompts, plugins, or orchestration to a .NET app; reviewing kernel construction, service registration, or plugin usage; building…

managedcode/dotnet-skills · 116 tokens