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-copilot-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/purview-copilot-oversharing)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-copilot-oversharing"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-copilot-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/purview-copilot-oversharing"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-copilot-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 | $0.00187 | $0.01394 |
| Opus 5 | $0.00093 | $0.00697 |
| Sonnet 5 | $0.00037 | $0.00279 |
| Haiku 4.5 | $0.00019 | $0.00139 |
Grade A, and why
purview-copilot-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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft 365 Copilot Oversharing Controls
Microsoft 365 Copilot honours existing permissions - so if content is overshared, Copilot can surface it to users who technically have access but shouldn't. This skill covers reducing that blast radius before and during Copilot rollout using SharePoint Advanced Management, sensitivity labels, restricted content discovery, and DLP for Copilot.
When to use
Preparing a tenant for Microsoft 365 Copilot and continuously controlling what Copilot can reach across SharePoint, OneDrive, and Teams.
Do not use this skill to monitor sensitive data in prompts (use purview-dspm-ai) or to design a
broader DLP program (use purview-dlp-policy).
Pick the right oversharing lever
| Symptom | Lever |
|---|---|
| "Everyone except external users" (EEEU) on too many sites | SAM data access governance report + permission cleanup |
| Sensitive content in broadly shared sites | Sensitivity labels (encrypt) + container labels for sites |
| Site shows up in Copilot results when it shouldn't | Restricted content discovery (RCD) on the site |
| Labelled content should be excluded from Copilot grounding | DLP for Microsoft 365 Copilot |
| Sharing links sprawl | SAM sharing link report + cleanup policies |
Rule of thumb: assess (DAG report) -> classify (labels) -> restrict (RCD, link policy) -> exclude (DLP for Copilot) -> govern (site lifecycle). Skipping the assess step is the most common failure.
Approach
- Assess - Use SharePoint Advanced Management (SAM) data access governance reports to find oversharing: "everyone/EEEU" access, broadly shared sites, sharing links, and permissioned but sensitive content. Verify: DAG report identifies top-N risky sites with owners.
- Engage site owners - Notify owners of risky sites with the remediation expected; do not remediate centrally without owner context. Verify: owner remediation tickets/issues opened with deadline.
- Classify & label - Apply sensitivity labels to sensitive content; container labels for sites; labels can encrypt and restrict, and Copilot respects label permissions. Verify: top-tier label encrypts and Copilot cannot surface the file to unauthorised test user.
- Restrict - Use restricted access control / restricted content discovery (RCD) on sensitive sites, tighten "everyone except external users" grants, and clean up sharing links. Verify: RCD-flagged site no longer appears in test user's Copilot answers.
- Apply DLP for Copilot - Use DLP for Microsoft 365 Copilot to exclude labelled content from Copilot processing where required. Verify: a test prompt referencing labelled content is excluded or warned.
- Govern lifecycle - Apply site lifecycle/access reviews to prevent regression; set inactive site policies in SAM. Verify: inactive sites archived or owners re-attested per cadence.
- Monitor with DSPM for AI - Continuously surface unlabelled sensitive files Copilot can access; loop back to label + restrict. Verify: weekly DSPM for AI report shrinks unlabelled-sensitive count.
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 · 96 lines · 187 tokens per session scan A 3d372bfb25f9
purview-copilot-oversharing is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 187 tokens to every session and 1,394 once invoked, about $0.0009 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.