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 insider-risk-baselinegit 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/insider-risk-baseline)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/insider-risk-baseline"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/insider-risk-baseline/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/insider-risk-baseline"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/insider-risk-baseline.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 | $0.00115 | $0.01297 |
| Opus 5 | $0.00057 | $0.00648 |
| Sonnet 5 | $0.00023 | $0.00259 |
| Haiku 4.5 | $0.00012 | $0.00130 |
Grade A, and why
insider-risk-baseline 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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview Insider Risk Management (Baseline)
Insider Risk Management (IRM) uses signals across Microsoft 365 and connected sources to detect, investigate, and act on risky insider activity - data theft, leaks, and policy violations - with privacy-by-design controls (pseudonymisation, RBAC, separation of duties).
When to use
Standing up an insider-risk program: departing-employee data theft, sensitive-data leaks, and security-policy violations - with legal/HR/privacy sponsorship in place.
Do not use this skill for risk-adaptive DLP design after IRM is running (use
purview-advanced-dlp) or for general communication compliance (use
purview-communication-compliance if available).
Pick the right starting policy template
| Concern | Template |
|---|---|
| Employees leaving with data | Data theft by departing users (needs HR connector for resignation/termination) |
| Sensitive-content leaks to unauthorised recipients | Data leaks (general / by priority users / by disgruntled users) |
| Security-policy violations (malware, AV disable, etc.) | Security policy violations |
| Risky AI usage | Risky AI usage (preview/GA as available) |
| Patient data / healthcare scenarios | Patient data leaks (sector-specific) |
Rule of thumb: pick one template per quarter, tune it to acceptable signal-to-noise, then add the next. Multiple templates active simultaneously without tuning swamps reviewers.
Approach
- Engage stakeholders - Bring legal, HR, privacy, and (where applicable) works councils to the design table; document the lawful basis for monitoring. Verify: signed-off scope document specifying data sources, retention, reviewer roles.
- Configure prerequisites - Set IRM settings, enable required indicators (Office, device, physical badging via connectors), and connect HR data via the Microsoft 365 HR connector for events like resignation/termination. Verify: HR connector status is healthy and a test resignation event appears within 24 hours.
- Choose policy templates - Start with templates: data theft by departing users, data leaks, security policy violations, and risky AI usage; configure scope. Verify: policy is in place with a defined user scope (pilot first) and indicator set.
- Privacy by design - Enable pseudonymisation of usernames, scope analyst/reviewer roles tightly (RBAC, separation of duties), and configure anonymisation per legal/works-council needs. Verify: reviewers see pseudonymised identifiers by default; un-anonymise requires elevated role.
- Triage & investigate - Review alerts, build cases, examine the user activity timeline, and escalate (e.g., to eDiscovery / HR) per the documented workflow. Verify: case management workflow exists with stages, owners, SLAs.
- Tune indicators and thresholds - Adjust thresholds to acceptable signal-to-noise; document tuning decisions for audit. Verify: alert volume per reviewer per week within the agreed range.
- Adaptive Protection - Feed IRM risk levels into Adaptive Protection so DLP/Conditional Access tighten dynamically for elevated-risk users. Verify: an elevated-risk test user triggers the stricter DLP branch.
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.
- 12d ago First seen · 94 lines · 115 tokens per session scan A 904d4bee8443
insider-risk-baseline is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 1,297 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 2026-08-30.
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.