Skills microsoft-foundry

📦

microsoft-foundry

Name: microsoft-foundry
Author: microsoft

v0.0.0-placeholder Content revision r1 Safe 🌐 Network access🔑 Env variables⚡ Contains scripts⚙️ External commands📁 Filesystem access

Manage Microsoft Foundry Agents

Foundry agent projects require coordinated setup across azd, Azure resources, models, tools, and evaluations. This skill guides Claude, Codex, and Claude Code through those workflows with project-specific checks and handoffs.

Supports: Claude Codex Code(CC)

📊 76 Adequate

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "microsoft-foundry" from https://skillstore.io/skills/microsoft-microsoft-foundry.md and its manifest at https://skillstore.io/api/skills/microsoft-microsoft-foundry/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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.

Markdown detail GET /skills/microsoft-microsoft-foundry.md Signed manifest GET /api/skills/microsoft-microsoft-foundry/manifest Signed lockfile GET /api/skills/microsoft-microsoft-foundry/lockfile

Test it

Using "microsoft-foundry". Create a new hosted Foundry agent from scratch.

Expected outcome:

The skill selects the quick-start create workflow, checks required Azure and azd context, asks for missing project choices, and outlines the deployment path.

Using "microsoft-foundry". Evaluate my deployed support agent and improve the prompt.

Expected outcome:

The skill identifies the observe workflow, prepares evaluation setup, recommends dataset and evaluator checks, and summarizes optimization actions for review.

Using "microsoft-foundry". Find a region with capacity for a model deployment.

Expected outcome:

The skill routes to model capacity guidance, compares available regions and quotas, and explains deployment tradeoffs before any Azure changes.

Security Audit

Safe

v6 • 7/20/2026 Open versioned report

All 400 representative static findings were adjudicated as false positives in context. They describe documented Azure Foundry administration, local project configuration, or guarded utility behavior; no prompt injection, credential exfiltration, or malicious intent was found. The skill can still execute cloud administration workflows, so users should review commands before applying changes. Static review was capped at 400/1141 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.

160

Files scanned

21,682

Lines analyzed

Review items

False positives ignored

Risk Factors

🌐 Network access (50)

🔑 Env variables (50)

⚡ Contains scripts (7)

finetuning/scripts/calibrate_grader.py:54 finetuning/scripts/calibrate_grader.py:54 finetuning/scripts/validate/validate_rft.py:200 foundry-agent/create/scripts/resolve-project-id.sh:278 foundry-agent/create/scripts/resolve-project-id.sh:283 references/sdk/foundry-sdk-py.md:47-50 references/sdk/foundry-sdk-py.md:133-135

⚙️ External commands (50)

📁 Filesystem access (50)

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: claude 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.

Open versioned report

Copy report link

https://skillstore.io/skills/microsoft-microsoft-foundry/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/microsoft-microsoft-foundry/security.svg)](https://skillstore.io/skills/microsoft-microsoft-foundry?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/microsoft-microsoft-foundry?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/microsoft-microsoft-foundry/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/microsoft-microsoft-foundry.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

microsoft. (2026). microsoft-foundry security audit report (audit version 6) [Author version 0.0.0-placeholder]. Skillstore. https://skillstore.io/skills/microsoft-microsoft-foundry/audits/6

BibTeX citation

@techreport{microsoft-microsoft-microsoft-foundry-2026,
  author = {microsoft},
  title = {microsoft-foundry security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/microsoft-microsoft-foundry/audits/6},
  note = {Author version 0.0.0-placeholder}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "microsoft-foundry security audit report (audit version 6)"
version: "0.0.0-placeholder"
type: report
authors:
  - name: "microsoft"
date-released: "2026-07-20"
url: "https://skillstore.io/skills/microsoft-microsoft-foundry/audits/6"
identifiers:
  - type: other
    value: "skillstore:microsoft-microsoft-foundry:audit:6"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create a Hosted Agent

Scaffold a hosted Foundry agent, connect it to a project, deploy it, and run a smoke test.

Evaluate Agent Quality

Build evaluation datasets, run batch evaluations, inspect traces, and optimize prompts or instructions.

Prepare Production Infrastructure

Plan resources, model capacity, quota, RBAC, networking, and deployment settings for Foundry workloads.

Try These Prompts

Start a Foundry Project

Help me create a new Azure AI Foundry project for a hosted agent. Ask for any missing subscription, region, and project details first.

Deploy a Hosted Agent

Review my current Foundry agent project, verify the azd environment, and guide me through a safe deployment and smoke test.

Improve Agent Quality

Set up an evaluation workflow for my Foundry agent, suggest datasets and evaluators, then help analyze failures and optimize instructions.

Plan Production Rollout

Create a production readiness plan for a Foundry agent, including RBAC, quota, model capacity, private networking, evaluation, and rollback checks.

Best Practices

Confirm the target subscription, resource group, project endpoint, agent root, and environment before write operations.
Prefer managed identity and project connections over raw API keys when a workflow supports both.
Keep generated evaluation artifacts under the selected .foundry folder and review them before deployment.

Avoid

Do not run deployment, quota, RBAC, or cleanup commands against an inferred subscription.
Do not paste secrets into prompts when managed identity, environment variables, or project connections can be used.
Do not reuse stale azd environment values across development, staging, and production projects.

Frequently Asked Questions

Does this skill create Azure resources?

It can guide resource creation workflows. Actual creation depends on available tools, permissions, and explicit user approval.

Can it manage existing Foundry agents?

Yes. It supports deployment, invocation, observation, tracing, troubleshooting, routines, and evaluation workflows for existing agents.

Does it require Azure CLI or azd?

Most hands-on workflows require Azure CLI, Azure Developer CLI, related extensions, and an authenticated Azure context.

Can it help with model deployment capacity?

Yes. It includes model deployment routing for preset deployments, custom settings, capacity discovery, quota, and region planning.

How does it handle secrets?

It prefers managed identity and project connections. Workflows that use environment files or API keys need careful redaction.

Is this only for Claude?

No. The report lists support for Claude, Codex, and Claude Code when those tools can access the skill files.

Developer Details

Author

microsoft

License

MIT

Author version

v0.0.0-placeholder

Skillstore revision

Repository

https://github.com/microsoft/github-copilot-for-azure/tree/main/plugin/skills/microsoft-foundry/

Ref

1200d2f84325e4a40a4c6cc230f3864179fd6940

Maintenance freshness

7/18/2026

Usage

8 downloads · 208 views

File structure