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 m365-oversharinggit 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/m365-oversharing)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/m365-oversharing"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/m365-oversharing/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/m365-oversharing"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/m365-oversharing.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 | $0.00203 | $0.01573 |
| Opus 5 | $0.00102 | $0.00787 |
| Sonnet 5 | $0.00041 | $0.00315 |
| Haiku 4.5 | $0.00020 | $0.00157 |
Grade A, and why
m365-oversharing 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft 365 Oversharing Remediation
Oversharing - content shared more broadly than it should be - is the root cause of most data exposure in Microsoft 365 and the biggest risk amplified by AI. Microsoft's Secure & Governed Data Foundation blueprint structures remediation into three pillars: remediate oversharing, set up guardrails, and meet regulations. The work is powered by SharePoint Advanced Management (SAM, included with a Microsoft 365 Copilot license), sensitivity and container labels, and Microsoft Purview.
When to use
Building a secure, well-governed Microsoft 365 data estate - reducing who can reach what across SharePoint, OneDrive, Teams, and Exchange, then keeping it that way with enforceable defaults. Applies whether or not Copilot is in scope; it is the data-foundation work every AI or data program depends on.
Do not use this skill when the question is purely Copilot rollout readiness framing (use
purview-copilot-oversharing), monitoring sensitive data in AI prompts (use purview-dspm-ai),
or designing a tenant-wide DLP program (use purview-dlp-policy).
The three pillars
| Pillar | Goal | Primary levers |
|---|---|---|
| Remediate oversharing | Find and reduce existing over-broad access fast | SAM data access governance (DAG) reports, EEEU cleanup, sharing-link cleanup, Restricted Access Control / Restricted Content Discovery |
| Set up guardrails | Prevent regression with enforceable defaults | Sensitivity + container labels, secure-by-default labelling, default sharing settings, site lifecycle policies |
| Meet regulations | Close audit/legal and AI-regulatory gaps | Purview Audit, Compliance Manager assessments, data hygiene |
Rule of thumb: assess -> classify -> restrict -> default-secure -> govern. Skipping the assess (DAG report) step is the most common failure; encrypting everything "to be safe" is the second.
Approach
- Assess (DAG reports) - Run SharePoint Advanced Management data access governance reports to find the riskiest sites: "Everyone Except External Users" (EEEU) on too many sites, broadly shared sites, sharing-link sprawl, and permissioned-but-sensitive content. Verify: DAG report ranks top-N risky sites with named owners.
- Apply interim restrictions - For the highest-risk sites, apply Restricted Access Control / Restricted Content Discovery as a fast interim guardrail while owners remediate. Verify: a restricted site no longer surfaces in a test user's search/Copilot results.
- Engage site owners - Notify owners with the expected fix; don't strip permissions centrally without owner context - that breaks legitimate collaboration and erodes trust. Verify: owner remediation tickets opened with deadlines.
- Classify & label - Apply sensitivity labels to sensitive content and container labels to sites; reserve encryption for genuinely sensitive content. Verify: a top-tier label encrypts and blocks unauthorised access.
- Secure by default - Use secure-by-default labelling (derive labels from SharePoint sites) and tighten default sharing settings so new content is protected without relying on users to remember to label. Verify: newly created content inherits a default label/sharing scope.
- Govern lifecycle - Apply site lifecycle and inactive-site policies plus access reviews so oversharing doesn't creep back; this is ongoing governance, not a one-time cleanup. Verify: inactive sites archived or owners re-attested on cadence.
- Meet regulations & monitor - Use Purview Audit and Compliance Manager to close audit/legal and AI-regulatory gaps, and monitor for new oversharing continuously. Verify: audit/regulatory assessment shows reducing exposure over time.
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 · 98 lines · 203 tokens per session scan A a469393ce827
m365-oversharing is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 203 tokens to every session and 1,573 once invoked, about $0.0010 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
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.