📦
content-creator
88Create Brand-Consistent Marketing Content
Marketing teams need content that stays consistent across channels. This skill helps plan, write, analyze, and optimize content for brand voice and SEO.
Writing & Content View
Skills agents-v2-py
📦
agents-v2-py
Content revision r2 Medium Risk ⚡ Contains scripts⚙️ External commands🌐 Network access🔑 Env variables
Build Container-Based Azure AI Hosted Agents
Deploying custom agent containers in Azure AI Foundry requires precise SDK, identity, registry, and protocol configuration. This skill provides focused Python patterns for creating and managing hosted agents.
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 "agents-v2-py" from https://skillstore.io/skills/sickn33-agents-v2-py.md and its manifest at https://skillstore.io/api/skills/sickn33-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 "agents-v2-py". Plan a hosted agent named invoice-reader using a fixed registry image and modest resources.
Expected outcome:
A deployment outline with prerequisite checks, authenticated client setup, a versioned image reference, response protocol configuration, one CPU, and two GiB memory.
Using "agents-v2-py". Explain why my hosted agent reports ImagePullBackOff.
Expected outcome:
- Confirm that the image path and fixed tag exist in the registry.
- Verify that the project managed identity has the AcrPull role.
- Check registry networking and retry after permission propagation.
Using "agents-v2-py". Design an asynchronous creation flow.
Expected outcome:
An async lifecycle plan that opens credential and project client contexts, creates one agent version, reports its state, and closes both clients.
Security Audit
Medium Riskv5 • 7/23/2026 Open versioned report
All 65 static findings are false positives caused by Markdown syntax, normal Python imports, example URLs, endpoint-only environment access, and troubleshooting text. Two contextual risks remain: copy-ready examples use mutable latest image tags, and an unguarded example deletes a cloud agent version. No prompt injection or malicious intent was found.
1
Files scanned
332
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (2)
Medium
Mutable Container Image Tags in Creation Examples
Copy-ready creation examples use the latest tag, so a moved registry tag can change which container code Azure executes.
Both executable examples explicitly reference latest, although the later best-practice section advises fixed production tags.
Low
Cloud Agent Version Deletion Without a Guard
The example directly deletes an Azure agent version without validating the target or requiring confirmation, creating accidental resource-loss risk.
The delete_version call is explicit and unguarded, but it targets a named version and is presented as an intentional management operation.
Risk Factors
⚡ Contains scripts (3)
⚙️ External commands (48)
SKILL.md:11 SKILL.md:15-17 SKILL.md:17-19 SKILL.md:19-23 SKILL.md:23-25 SKILL.md:25-32 SKILL.md:32-33 SKILL.md:33-34 SKILL.md:34-38 SKILL.md:38-40 SKILL.md:40-49 SKILL.md:49-55 SKILL.md:55-64 SKILL.md:64-68 SKILL.md:68-92 SKILL.md:92-96 SKILL.md:96-100 SKILL.md:100-104 SKILL.md:104-109 SKILL.md:109-115 SKILL.md:115 SKILL.md:116 SKILL.md:117 SKILL.md:118 SKILL.md:119 SKILL.md:120 SKILL.md:124-126 SKILL.md:126-133 SKILL.md:133-138 SKILL.md:138-144 SKILL.md:144-151 SKILL.md:151-165 SKILL.md:165-167 SKILL.md:167-171 SKILL.md:171-180 SKILL.md:180-184 SKILL.md:184-194 SKILL.md:194-200 SKILL.md:200-207 SKILL.md:207-213 SKILL.md:213-263 SKILL.md:263-267 SKILL.md:267-300 SKILL.md:300-306 SKILL.md:306 SKILL.md:307-308 SKILL.md:308-309 SKILL.md:309
🌐 Network access (6)
🔑 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-agents-v2-py/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-agents-v2-py?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-agents-v2-py?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-agents-v2-py/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-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 · BibTeX · CFF)
APA citation
sickn33. (2026). agents-v2-py security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-agents-v2-py/audits/5BibTeX citation
@techreport{sickn33-sickn33-agents-v2-py-2026,
author = {sickn33},
title = {agents-v2-py security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-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: "agents-v2-py security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-agents-v2-py/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-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
Create a First Hosted Agent
Prepare a Python workflow that authenticates and deploys a custom container as an Azure AI hosted agent.
Standardize Deployment Configuration
Define consistent protocols, resources, tools, image references, and environment settings for hosted agent releases.
Diagnose Hosted Agent Failures
Review registry permissions, image paths, capability hosts, and protocol versions when agent creation fails.
Try These Prompts
Check Prerequisites
Review my Azure AI project setup for a container-based hosted agent. Identify missing SDK, registry, identity, capability host, and endpoint requirements.
Draft Agent Creation
Create a Python hosted-agent workflow for image [image reference], agent [name], CPU [value], and memory [value]. Use DefaultAzureCredential and fixed image tags.
Configure Tools and Runtime
Extend my hosted-agent design with [tools], protocol [protocol], and these non-secret environment settings: [settings]. Explain required permissions and trust boundaries.
Review a Production Design
Audit this Azure hosted-agent deployment plan: [plan]. Check image immutability, least privilege, secret handling, MCP trust, resource sizing, cleanup controls, and async lifecycle management.
Best Practices
- Use immutable image digests or fixed version tags for repeatable deployments.
- Grant only required registry and project permissions through managed identities.
- Validate tool endpoints, protect secrets, and confirm destructive operations before execution.
Avoid
- Do not deploy production agents from mutable latest image tags.
- Do not place credentials or secrets directly in source code or container settings.
- Do not enable code execution, file access, or MCP tools without reviewing their trust boundaries.
Frequently Asked Questions
Which Python packages are required?
The examples use azure-ai-projects version 2.0.0b3 or later and azure-identity.
How does authentication work?
The skill uses DefaultAzureCredential, which can select supported local or managed Azure identities.
Must the container image be in Azure Container Registry?
The documented workflow assumes Azure Container Registry and requires the project managed identity to have pull access.
Can I configure tools for the hosted agent?
Yes. Examples cover code interpreter, file search, and MCP tools, but each tool requires a security review.
Does the skill support asynchronous Python?
Yes. It includes an async pattern using Azure credential and project client context managers.
Does this skill deploy Azure infrastructure?
No. It documents hosted-agent SDK operations and assumes the required Azure resources and permissions already exist.
Developer Details
Author
sickn33License
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006
Maintenance freshness
7/26/2026
Usage
5 downloads · 117 views
File structure
📄 SKILL.md
More from sickn33
View all📦
prompt-engineering-patterns
85Improve LLM Prompts With Proven Patterns
Inconsistent prompts waste time and make AI outputs hard to trust. This skill guides prompt design with reusable patterns, examples, evaluation steps, and optimization workflows.
Productivity View
📦
senior-fullstack
82Build Fullstack Apps with Senior Patterns
Teams need consistent setup, architecture, and review guidance for modern web applications. This skill provides scaffolders, workflow references, and quality prompts for React, Next.js, Node.js, GraphQL, and PostgreSQL projects.
Coding & Development View
📦
senior-architect
81Design Scalable Software Architectures
Architecture decisions are hard to compare across web, mobile, backend, and cloud systems. This skill provides structured guides and local scaffold scripts for reports, dependency review, and trade-off documentation.
Coding & Development View
📦
prompt-engineer
81Optimize AI Prompts With Prompt Engineer
Writing clear prompts is hard when goals are vague or complex. This skill turns rough requests into structured prompts using proven prompt frameworks.
Productivity View
📦
product-manager-toolkit
80Prioritize Product Work With Research Insights
Product teams need faster ways to rank features, synthesize interviews, and document decisions. This skill provides RICE scoring, interview analysis, and PRD templates for structured planning.
Productivity View
Related Skills
View all📦
python-async-patterns
85Build Reliable Async Python
by 0xDarkMatter
Async Python code often fails due to blocking calls, unbounded tasks, and weak cleanup. This skill provides reusable asyncio patterns, examples, and references for robust concurrent services.
Coding & Development View
📦
python-fastapi-patterns
85Build FastAPI APIs with Reusable Patterns
by 0xDarkMatter
FastAPI projects need consistent choices for validation, dependencies, middleware, and background work. This skill gives Claude, Codex, and Claude Code reusable patterns for practical Python API development.
Coding & Development View
📦
python-typing-patterns
85Add Python Type Safety Patterns
by 0xDarkMatter
Python type annotations can be hard to apply consistently across real projects. This skill gives Claude, Codex, and Claude Code practical patterns for safer typed Python code.
Coding & Development View
📦
tdd-pytest
81Build Python Tests with pytest TDD
by 89jobrien
Python teams often need consistent tests, coverage, and reports without losing TDD discipline. This skill provides pytest-focused workflows, examples, and reporting guidance for Claude, Codex, and Claude Code.
Coding & Development View
📦
enact-hello-python
81Run a Python Greeting Example
by EnactProtocol
New Enact users need a small example that proves tool execution works. This skill runs a Python greeting command and returns simple runtime output.
Coding & Development View
📦
dead-code-removal
80Remove Dead Code Safely
by 89jobrien
Unused imports, functions, and classes increase maintenance cost and deployment size. This skill guides Claude, Codex, and Claude Code through conservative analysis, backups, removal, and validation.
Coding & Development View