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.
npx skills add vinayaklatthe/microsoft-security-skills --skill purview-dspm-aigit clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skillsWrote 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.
[](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-dspm-ai)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-dspm-ai"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-dspm-ai/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.
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-dspm-ai"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-dspm-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00212 | $0.01335 |
| Opus 5 | $0.00106 | $0.00668 |
| Sonnet 5 | $0.00042 | $0.00267 |
| Haiku 4.5 | $0.00021 | $0.00134 |
Grade A, and why
purview-dspm-ai 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview DSPM for AI
DSPM for AI gives visibility and control over how sensitive data is used in generative AI - Microsoft 365 Copilot, Security Copilot, Copilot Studio agents, and third-party/consumer AI apps (ChatGPT, Gemini, Claude) - and recommends protections you can apply in one click.
When to use
Securing and governing data interactions with AI as Copilot and genAI adoption grows in the tenant, especially before broad rollout.
Do not use this skill when the goal is to clean up SharePoint permissions ahead of Copilot
(use purview-copilot-oversharing) or to investigate insider activity (use insider-risk-baseline).
Pick the right starting lens
| Concern | Start here |
|---|---|
| Are users pasting sensitive data into ChatGPT? | DSPM for AI - Activity Explorer + Edge browser extension / Defender for Cloud Apps signals |
| What sensitive data is Copilot retrieving? | DSPM for AI - Data assessments + interaction reports |
| Are prompts/responses violating policy? | Communication Compliance for Copilot + DLP for AI |
| Files Copilot can reach but shouldn't | DSPM for AI - unlabelled sensitive files report (then purview-copilot-oversharing) |
Rule of thumb: turn on DSPM for AI first to see the risk surface, then action the one-click recommendations rather than building bespoke policies from scratch.
Approach
- Onboard DSPM for AI - Activate from the Purview portal; consent to the analytics it needs and confirm Audit is enabled tenant-wide. Verify: the DSPM for AI overview shows interaction counts within 24-48 hours.
- Run the data assessments - Execute the oversharing assessment and Copilot interactions assessment to scope risk before enforcement. Verify: assessment results identify top sites/users by sensitive interaction volume.
- Action one-click recommendations - Apply the recommended policies: detect risky AI interactions, extend sensitivity labels to AI, and protect data referenced by Copilot. Verify: each accepted recommendation creates a corresponding Purview policy in audit mode.
- Govern third-party AI - Pair with Defender for Cloud Apps to discover ChatGPT/Gemini/Claude use; apply Endpoint DLP rules to block paste of labelled content into unsanctioned AI apps. Verify: Cloud App Catalog shows AI app risk scores and DLP blocks appear in Activity Explorer.
- Apply DLP for AI - Use DLP policies for Microsoft 365 Copilot to exclude labelled content from Copilot processing or restrict by group; use Communication Compliance for prompt review. Verify: a test prompt referencing a labelled document is excluded or flagged.
- Operate - Review Activity Explorer weekly, tune false positives, and report metrics (interactions classified, recommendations accepted, blocks) to leadership.
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 · 86 lines · 212 tokens per session scan A b30d11be1665
purview-dspm-ai is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 1,335 once invoked, about $0.0011 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.
Other skills, from other repositories
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement.
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.
session-rag-eval
Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.
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…
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…