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-advanced-dlpgit 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-advanced-dlp)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-advanced-dlp"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-advanced-dlp/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-advanced-dlp"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-advanced-dlp.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 | $0.00107 | $0.01238 |
| Opus 5 | $0.00053 | $0.00619 |
| Sonnet 5 | $0.00021 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
purview-advanced-dlp 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview Advanced DLP
Advanced DLP extends baseline policies with risk-adaptive and high-precision controls, notably Adaptive Protection, which dynamically adjusts DLP enforcement based on a user's Insider Risk level - so low-risk users get light controls and elevated-risk users get stricter actions automatically.
When to use
Moving from static DLP to dynamic, context-aware enforcement and high-precision matching for mature data security programs that already have classification and baseline DLP working.
Do not use this skill to design a first DLP policy from scratch (use purview-dlp-policy) or to
stand up Insider Risk Management (use insider-risk-baseline).
Pick the right advanced capability
| Goal | Use |
|---|---|
| Dynamic enforcement keyed to user risk | Adaptive Protection (IRM-driven) |
| High-precision match against your own records | Exact Data Match (EDM) SITs |
| Context-aware rules (label + recipient + volume) | Contextual conditions in DLP rules |
| Block USB / unsanctioned cloud / clipboard | Advanced Endpoint DLP egress controls |
| Stop paste into ChatGPT / unsanctioned AI | Endpoint DLP + DSPM for AI |
Rule of thumb: pick one advanced capability per quarter; layering Adaptive Protection, EDM, and new Endpoint controls simultaneously makes failure attribution impossible.
Approach
- Confirm prerequisites - Baseline DLP in enforce mode for at least one workload; Insider Risk Management running with tuned indicators (for Adaptive Protection). Verify: IRM is producing meaningful risk levels for a pilot population.
- Adaptive Protection - Integrate Insider Risk Management risk levels (minor/moderate/ elevated) with DLP so low-risk users get light controls and elevated-risk users get stricter actions (e.g., block) automatically - minimising friction while focusing protection. Verify: a test user moved to elevated triggers the stricter DLP rule branch.
- Exact Data Match (EDM) - Use EDM SITs to match against a hashed copy of your structured data (e.g., customer records) for high-precision, low-false-positive detection. Verify: EDM schema definition uploaded, hash refresh succeeded, and test sample matches.
- Contextual conditions - Combine sensitivity labels, classifiers, content volume, recipient, and access scope for precise rules (e.g., "Confidential + external recipient + ≥5 SIT matches"). Verify: test events show the rule fires only on the intended combinations.
- Endpoint egress controls - Restrict copy to USB, upload to unsanctioned cloud/AI apps, network share, clipboard, and printing on managed endpoints. Verify: a test paste of labelled content into an unsanctioned AI app is blocked or flagged.
- Tune continuously - Use Activity Explorer and alerts to refine; review override justifications weekly. Verify: false-positive rate trends down month over month.
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 · 92 lines · 107 tokens per session scan A 43656d14df35
purview-advanced-dlp is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,238 once invoked, about $0.0005 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
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-writing-plans
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.
bf-to-agents-sdk-dotnet-migration
Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.