Skills m365-agents-py
📦
m365-agents-py
Content revision r1 Medium Risk ⚡ Contains scripts⚙️ External commands🌐 Network access📁 Filesystem access🔑 Env variables
Build Microsoft 365 Python Agents
Teams and Copilot Studio agent projects require accurate SDK patterns, routing, streaming, and authentication setup. This skill gives Claude, Codex, and Claude Code focused Python guidance for Microsoft 365 Agents SDK implementations.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "m365-agents-py" from https://skillstore.io/skills/sickn33-m365-agents-py.md and its manifest at https://skillstore.io/api/skills/sickn33-m365-agents-py/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-py". Build a Teams agent that replies to status and welcome messages.
Expected outcome:
- A concise implementation plan for aiohttp hosting and AgentApplication routing.
- A list of required Microsoft Agents SDK packages and configuration values.
- Security notes for JWT middleware, local development secrets, and production storage.
Using "m365-agents-py". Add a signed-in Microsoft Graph profile command.
Expected outcome:
- A step-by-step authentication design using MSAL and auth handlers.
- Recommended consent, scope, and token-handling checks.
- User-facing response guidance that avoids exposing unnecessary profile data.
Using "m365-agents-py". Connect my agent to Copilot Studio.
Expected outcome:
- A Copilot Studio connection checklist for tenant, environment, schema, and app registration values.
- A conversation flow outline for starting a session and sending user questions.
- Warnings about broad scopes, token cache storage, and production observability.
Security Audit
Medium Riskv4 • 7/7/2026 Open versioned report
Most static findings are false positives from Markdown fences, inline backticks, static Python imports, placeholders, and reference links. Confirmed risks are limited to low-severity dotenv and authenticated Microsoft Graph examples, with a medium semantic concern around broad OAuth .default scope usage. No prompt-injection attempt or malicious data-exfiltration intent was found.
1
Files scanned
346
Lines analyzed
4
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Broad OAuth Default Scope in Copilot Studio Example
The Copilot Studio token request uses the Power Platform .default scope, which can request all pre-consented permissions for that resource. Production guidance should narrow or explicitly justify scopes.
The exact .default scope is present in the token request, and broad default scopes are a known permission-governance risk. The surrounding code is legitimate, so severity is medium rather than high.
Low
Authenticated Profile Data Returned to Chat
The Graph profile example retrieves signed-in user data and sends the display name back into the conversation. This may expose profile data in chat transcripts if copied without data-minimization review.
The sample directly obtains a user token, calls the Graph profile endpoint, and sends displayName to chat. It is expected behavior but still creates a privacy review requirement.
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Low
HTTP client library
async def profile_request(context: TurnContext, state: TurnState):
The surrounding OAuth example uses aiohttp to make an authenticated Microsoft Graph request with a user bearer token. This is expected for the skill, but it is security-sensitive network and token handling.
Low
Hardcoded URL
"https://graph.microsoft.com/v1.0/me", headers=headers
The example sends a user OAuth bearer token to Microsoft Graph and retrieves profile data. The endpoint is legitimate, but copied implementations need consent, scope, and data-minimization controls.
Low
dotenv library
load_dotenv()
The sample calls load_dotenv(), which can import local .env secrets into the process. This is common configuration practice, but it requires strict source-control and secret-management discipline.
Low
Python dotenv loader
load_dotenv()
The actual dotenv loader call reads local environment configuration. It is legitimate for Microsoft app credentials but still handles sensitive values.
Risk Factors
⚡ Contains scripts (4)
⚙️ External commands (21)
SKILL.md:18 SKILL.md:22-29 SKILL.md:29-33 SKILL.md:33-51 SKILL.md:51-55 SKILL.md:55-128 SKILL.md:128-132 SKILL.md:132-183 SKILL.md:183-187 SKILL.md:187-229 SKILL.md:229-233 SKILL.md:233-256 SKILL.md:256-260 SKILL.md:260-319 SKILL.md:319-323 SKILL.md:323-324 SKILL.md:324-325 SKILL.md:325-326 SKILL.md:326-327 SKILL.md:327-328 SKILL.md:328-329
🌐 Network access (9)
📁 Filesystem access (2)
🔑 Env variables (7)
Audited by: codex View Audit History →
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-py/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-m365-agents-py?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-m365-agents-py?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-m365-agents-py/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-m365-agents-py.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-py security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-m365-agents-py/audits/4BibTeX citation
@techreport{sickn33-sickn33-m365-agents-py-2026,
author = {sickn33},
title = {m365-agents-py security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/sickn33-m365-agents-py/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-py 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-py/audits/4"
identifiers:
- type: other
value: "skillstore:sickn33-m365-agents-py:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance
What You Can Build
Create a Teams Agent Prototype
Generate a Python agent skeleton with aiohttp hosting, message routing, and JWT middleware.
Add Enterprise Authentication
Plan MSAL configuration, auth handlers, token retrieval, and Microsoft Graph profile access.
Connect Copilot Studio Workflows
Design direct Copilot Studio client flows that start conversations and pass user questions.
Try These Prompts
Start a Basic Agent
Create a minimal Microsoft 365 Agents SDK Python agent using aiohttp hosting, message routing, and safe local configuration.
Add Message Routing
Design AgentApplication routes for welcome events, status commands, regex matches, invoke activities, fallback handling, and errors.
Implement Authenticated Graph Access
Add MSAL-backed OAuth handling for a Graph profile request, including consent checks, token handling, and safe response behavior.
Review a Production Architecture
Review this Microsoft 365 agent architecture for production readiness, including storage, tenant isolation, streaming, logging, secrets, and Copilot Studio access.
Best Practices
- Verify current Microsoft Agents SDK APIs before generating final implementation code.
- Use environment variables or managed secret stores, and never commit tenant secrets.
- Limit OAuth scopes, validate tenant configuration, and review consent before deployment.
Avoid
- Do not copy sample `.default` scopes into production without permission review.
- Do not use MemoryStorage for production conversations or user state.
- Do not log OAuth tokens, profile data, or Copilot Studio conversation content.
Frequently Asked Questions
What does this skill help build?
It helps build Python agents for Microsoft 365, Teams, and Copilot Studio using Microsoft Agents SDK patterns.
Does it create a complete production service?
No. It provides implementation guidance and examples that need testing, deployment work, and tenant-specific review.
Which AI tools can use it?
The report lists compatibility with Claude, Codex, and Claude Code.
Does it require Microsoft credentials?
Yes. Real projects need tenant values, app registrations, OAuth settings, and secret management outside source control.
Can it help with streaming responses?
Yes. It includes guidance for Azure OpenAI streaming and closing streaming responses safely.
What should be reviewed before publishing an agent?
Review scopes, consent, storage, logging, tenant isolation, middleware, and current Microsoft SDK documentation.