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-communication-compliancegit 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-communication-compliance)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/purview-communication-compliance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-communication-compliance/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-communication-compliance"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/purview-communication-compliance.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 | $0.00090 | $0.00955 |
| Opus 5 | $0.00045 | $0.00477 |
| Sonnet 5 | $0.00018 | $0.00191 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
purview-communication-compliance 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Purview Communication Compliance
Communication Compliance detects, captures, and helps remediate inappropriate or risky messages (harassment, threats, sensitive-data sharing, regulatory violations, and risky AI prompts) across Exchange, Teams, Viva Engage, and connected third-party communications.
When to use
Meeting regulatory communication-supervision obligations and detecting code-of-conduct or data-leak risks in messaging.
Approach
- Define policies — Use templates (offensive language/harassment, sensitive info, regulatory compliance) and scope users/groups, channels, and conditions (SITs, trainable classifiers, keywords).
- Protect privacy — Enable pseudonymisation of usernames for reviewers, scope reviewer access strictly (RBAC), and separate duties so monitoring respects worker privacy.
- Review & remediate — Triage alerts, tag/resolve, escalate, notify, or take action; document the workflow for auditability.
- Tune — Adjust classifiers/conditions to reduce noise; use intelligent features to reduce false positives.
- Integrate — Feed signal into Insider Risk Management where appropriate.
Guardrails
- Respect privacy and works-council/legal requirements — pseudonymisation and least-privilege reviewers are essential; consult legal/HR before rollout.
- Start narrow (specific risks/groups), then expand.
- Reviewer access to message content is highly sensitive — audit it.
Common scenarios
- Regulatory supervision (financial services). Supervise broker-dealer and advisor communications for FINRA/SEC obligations: scope a policy to the regulated population, use the regulatory-compliance template, detect off-channel comms and undisclosed promises, and route matches to compliance reviewers with documented disposition for audit.
- Code-of-conduct / harassment detection. Detect threats, harassment, and offensive language across Teams and Viva Engage using the offensive-language trainable classifier; pseudonymise usernames so reviewers triage behaviour, not identities, and escalate confirmed cases to HR.
- Sensitive-data oversharing in chat. Catch credentials, PII, or financial data pasted into Teams or email by combining sensitive info types (SITs) and labels as policy conditions, then feed confirmed signals into Insider Risk Management.
- Risky AI / Copilot prompts. Detect inappropriate or data-leaking prompts and responses in AI interactions (including Microsoft 365 Copilot) so risky generative-AI usage is supervised alongside human messaging.
- Connected third-party communications. Extend supervision beyond Microsoft 365 by ingesting data from connected platforms (for example Bloomberg, Slack, or other sources via data connectors) so a single policy set covers regulated channels outside Exchange and Teams.
- Departing-employee leak watch. Pair a sensitive-info policy with HR-driven scope (leavers) to spot data being forwarded or shared externally before a departure date.
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 · 72 lines · 90 tokens per session scan A 240e7fa53183
purview-communication-compliance is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 955 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
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.