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-dlp-policygit 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-dlp-policy)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-dlp-policy"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-dlp-policy/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-dlp-policy"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-dlp-policy.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 | $0.00120 | $0.01275 |
| Opus 5 | $0.00060 | $0.00638 |
| Sonnet 5 | $0.00024 | $0.00255 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
purview-dlp-policy 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview DLP Policy
Microsoft Purview Data Loss Prevention (DLP) detects and prevents risky sharing, transfer, or use of sensitive data across Microsoft 365 services and Windows/macOS endpoints - anchored to the Zero Trust Data pillar.
When to use
Stopping exfiltration of sensitive content (PII, financial, IP, regulated data) across email, collaboration, and endpoints with a defensible, tunable policy set.
Do not use this skill for risk-adaptive DLP keyed to Insider Risk (use purview-advanced-dlp)
or for Copilot-specific exclusion (use purview-copilot-oversharing).
Pick the right starting policy per workload
| Workload | Start with | Notes |
|---|---|---|
| Exchange Online | Block external send of high-volume SIT matches | Policy tips + override + justification |
| SharePoint / OneDrive | Warn on external sharing of labelled content | Service-side detection |
| Teams | Warn on chat/channel post containing SITs | Applies post-creation only |
| Endpoint (Windows/Mac) | Audit USB copy, then warn, then block | Needs onboarded devices + E5 Compliance |
| All | Simulation mode for 7-14 days first | No exceptions |
Rule of thumb: one policy per workload, severity-tiered actions, simulation always, exceptions defined before block.
Approach
- Locations - Choose locations explicitly: Exchange, SharePoint, OneDrive, Teams, and Endpoint (a single policy does not cover all locations by default). Endpoint DLP requires onboarded devices and E5 Compliance. Verify: each policy lists only the locations it intends to cover; Endpoint shows onboarded device count > 0.
- Conditions - Match on SITs, sensitivity labels, trainable classifiers, and content volume thresholds (e.g., 5+ credit-card numbers); combine for precision. Verify: a test document matches the rule with expected confidence and volume.
- Actions by severity - Low = audit only; Medium = warn with override + justification; High = block + notify. Configure policy tips and incident reports. Verify: each severity branch fires the intended action in a test event.
- Simulation first - Run in simulation mode (7-14 days), review matches in Activity Explorer, tune false positives, then promote to enforcement. Verify: simulation report shows match volume and false-positive rate within target before enforcement.
- Exceptions - Define trusted recipients/domains and business-justification overrides so legitimate processes aren't blocked. Verify: documented exception list reviewed by data owner; override workflow tested.
- Endpoint DLP onboarding - Onboard devices via Defender for Endpoint or Intune, confirm policy reaches them, and start in audit before warn/block. Verify: endpoint policy status shows successful sync per device.
- Operate - Route incidents to a shared compliance mailbox; review override justifications weekly; tune monthly. Verify: incident triage SLA defined and met; tuning log maintained.
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 · 93 lines · 120 tokens per session scan A 61ab226b4f9b
purview-dlp-policy is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,275 once invoked, about $0.0006 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
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…
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…
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-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-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…
compliance-verifier
Use this agent to validate deployments against GDPR, HIPAA, SOC2, and other regulatory compliance frameworks and generate audit reports.