m365-agents-ts
Build Microsoft 365 Agents in TypeScript
Developers need reliable patterns for Microsoft 365 agents across Teams and Copilot Studio. This skill provides TypeScript examples for routing, hosting, streaming, and Copilot Studio integration.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "m365-agents-ts" from https://skillstore.io/skills/sickn33-m365-agents-ts.md and its manifest at https://skillstore.io/api/skills/sickn33-m365-agents-ts/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "m365-agents-ts". Plan a starter Microsoft 365 agent for Teams using TypeScript.
Expected outcome:
A concise build plan with packages, hosting choices, routing handlers, configuration needs, and documentation checks before coding.
Using "m365-agents-ts". Review a streaming response handler for a Teams agent.
Expected outcome:
A focused review covering progress updates, sensitivity labels, stream completion, error handling, and safe Azure OpenAI configuration.
Using "m365-agents-ts". Choose a Copilot Studio integration approach.
Expected outcome:
A comparison of direct client and WebChat options, including setup needs, token handling, user experience, and deployment considerations.
Security Audit
SafeStatic analysis mainly flagged Markdown code fences, documentation links, and environment variable examples in SKILL.md. No prompt injection, credential exfiltration, or malicious automation intent was found. The skill is documentation-oriented, but authors should keep stronger warnings around secrets and production validation.
Risk Factors
⚙️ External commands (15)
🌐 Network access (7)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-m365-agents-ts/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-m365-agents-ts?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-m365-agents-ts?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-m365-agents-ts/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-m365-agents-ts.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). m365-agents-ts security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-m365-agents-ts/audits/4BibTeX citation
@techreport{sickn33-sickn33-m365-agents-ts-2026,
author = {sickn33},
title = {m365-agents-ts security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/sickn33-m365-agents-ts/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "m365-agents-ts security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-m365-agents-ts/audits/4"
identifiers:
- type: other
value: "skillstore:sickn33-m365-agents-ts:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Create a Teams agent starter
Use the hosting and routing examples to plan a basic TypeScript agent for Teams or Microsoft 365.
Plan Copilot Studio integration
Compare direct client and WebChat patterns before connecting an existing Copilot Studio agent.
Add streaming answers
Use the streaming response pattern to design long-running Azure OpenAI responses with status updates.
Try These Prompts
Create a TypeScript starter plan for a Microsoft 365 agent using AgentApplication and Express hosting. Include required packages and main files.
Help me design message and conversation update handlers for a Teams agent. Keep each handler focused and explain required TurnContext use.
Design a streaming response flow for Azure OpenAI in a Microsoft 365 agent. Include labels, progress updates, and final stream cleanup.
Review my Microsoft 365 Agents SDK design for production readiness. Check authentication, environment variables, logging, error handling, and Copilot Studio integration.
Best Practices
- Verify current Microsoft SDK signatures before generating final code.
- Keep secrets in managed stores or environment variables, and validate them at startup.
- Add authentication, payload validation, and redacted logging before production deployment.
Avoid
- Do not paste real API keys, client secrets, or bearer tokens into prompts or source files.
- Do not treat the snippets as a complete production security model.
- Do not log invoke payloads or Copilot replies without review and redaction.