Skills hosted-agents-v2-py
๐Ÿ“ฆ

hosted-agents-v2-py

Content revision r2 Safe โšก Contains scriptsโš™๏ธ External commands๐ŸŒ Network access๐Ÿ”‘ Env variables

Build Azure AI Hosted Agents with Python

Container-based Azure agents require precise SDK, identity, image, and protocol configuration. This skill provides focused Python patterns for creating and managing hosted agents.

Supports: Claude Codex Code(CC)
๐Ÿฅ‰ 78 Bronze

Install with my Agent

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

Agent request
Review the Skillstore skill "hosted-agents-v2-py" from https://skillstore.io/skills/sickn33-hosted-agents-v2-py.md and its manifest at https://skillstore.io/api/skills/sickn33-hosted-agents-v2-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 "hosted-agents-v2-py". Plan a hosted agent for a data processor image with two CPUs and four GiB of memory.

Expected outcome:

  • Prerequisites: Azure AI project, accessible registry image, managed identity pull permission, and account capability host.
  • Configuration: Responses protocol version v1, two CPUs, four GiB memory, and a versioned image tag.
  • Validation: confirm image access, create the agent version, inspect its state, and remove unused versions.

Using "hosted-agents-v2-py". Explain why my hosted agent reports ImagePullBackOff.

Expected outcome:

The project managed identity likely lacks registry pull access. Verify the image path, then grant the identity the AcrPull role.

Using "hosted-agents-v2-py". Compare synchronous and asynchronous hosted agent creation.

Expected outcome:

Both approaches use the same agent definition. The asynchronous pattern also manages credential and client lifecycles with asynchronous context managers.

Security Audit

Safe
v5 โ€ข 7/24/2026 Open versioned report

All 65 static alerts are false positives caused by Markdown syntax, Python imports, configuration placeholders, or documentation links. No malicious intent, secret access, command execution, or prompt injection was found.

1
Files scanned
332
Lines analyzed
0
Review items
0
False positives ignored
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: codex View Audit History โ†’
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
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-hosted-agents-v2-py/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-hosted-agents-v2-py/security.svg)](https://skillstore.io/skills/sickn33-hosted-agents-v2-py?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-hosted-agents-v2-py?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-hosted-agents-v2-py/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-hosted-agents-v2-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 ยท BibTeX ยท CFF)

APA citation

sickn33. (2026). hosted-agents-v2-py security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-hosted-agents-v2-py/audits/5

BibTeX citation

@techreport{sickn33-sickn33-hosted-agents-v2-py-2026, author = {sickn33}, title = {hosted-agents-v2-py security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/sickn33-hosted-agents-v2-py/audits/5}, 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: "hosted-agents-v2-py security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-24" url: "https://skillstore.io/skills/sickn33-hosted-agents-v2-py/audits/5" identifiers: - type: other value: "skillstore:sickn33-hosted-agents-v2-py:audit:5" 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

Prototype a hosted agent

Create a first hosted agent version from an existing container image with basic resource settings.

Standardize agent deployment

Prepare repeatable SDK patterns for image versions, protocols, tools, and resource allocation.

Diagnose deployment failures

Map common hosted agent errors to registry permissions, image paths, capability hosts, and protocol settings.

Try These Prompts

Plan a basic hosted agent
Plan a Python hosted agent named [agent name] using image [image path]. List required Azure resources and configuration values.
Create a hosted agent
Create a Python implementation for [agent name] using [image path]. Use DefaultAzureCredential and configure [CPU] CPU with [memory] memory.
Add tools and asynchronous access
Adapt my hosted agent for asynchronous creation. Add [tool list], preserve secure authentication, and explain required container environment variables.
Review a production deployment
Review my hosted agent design for production. Assess image versioning, permissions, resources, protocols, cleanup, error handling, and secret management.

Best Practices

  • Use immutable image tags for production deployments.
  • Grant only required registry permissions to the project managed identity.
  • Store secrets in Azure Key Vault and pass only necessary configuration to containers.

Avoid

  • Do not use the latest image tag for production agent versions.
  • Do not hardcode credentials or secrets in source code or container definitions.
  • Do not create agents before validating registry access and capability host configuration.

Frequently Asked Questions

Which Python packages are required?
Install azure-ai-projects version 2.0.0b3 or later and azure-identity.
How does the skill authenticate to Azure?
It uses DefaultAzureCredential, which supports local development identities and managed identities.
Can this skill build my container image?
No. It expects an existing image in a registry accessible to the Azure project.
Which hosted agent protocol is shown?
The examples use the Responses protocol with version v1.
Can I configure tools and resources?
Yes. The agent definition supports tools, CPU, memory, protocol versions, image paths, and environment variables.
Does the skill support asynchronous Python?
Yes. It includes an asynchronous pattern for credentials, the project client, and agent creation.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Ref

88a8e9a07f4c54ab105c1c41b6267c287146b07b

Maintenance freshness

7/26/2026

Usage

6 downloads ยท 136 views

File structure

๐Ÿ“„ SKILL.md