red-team-agent-orchestration: Skill for Claude Code

.agents/skills/azure-redteam-ai/SKILL.md

azure-redteam-ai is a skill for Claude Code, Codex from Contoso-State/red-team-agent-orchestration. It costs 121 tokens per session (724 once invoked), scanned A, original, MIT.

A security assessment guide for Azure AI services, including Azure OpenAI, AI Services, AI Foundry and Azure Machine Learning. A red-team engagement is an authorised exercise that looks for ways systems could be exposed or abused.

In plain words
What is it for?
Checking network exposure, authentication, content-safety settings, identity permissions and access to connected data in Azure AI environments.
Why use it?
It helps find publicly reachable AI endpoints, weak authentication, missing safety controls and overly broad permissions before attackers exploit them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Contoso-State/red-team-agent-orchestration's own configuration. It tells Claude Code and Codex how to work on red-team-agent-orchestration itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything red-team-agent-orchestration configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Contoso-State/red-team-agent-orchestration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Contoso-State/red-team-agent-orchestration/main/.agents/skills/azure-redteam-ai/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestration

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for azure-redteam-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai/github.svg)](https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai)
Your own site
<a href="https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai"><img src="https://agentmods.dev/badge/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for azure-redteam-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai"><img src="https://agentmods.dev/badge/skills/contoso-state/red-team-agent-orchestration/azure-redteam-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.00724
Opus 5 $0.00060 $0.00362
Sonnet 5 $0.00024 $0.00145
Haiku 4.5 $0.00012 $0.00072

Measured 12d ago against content hash c962ccb966ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

azure-redteam-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/azure-redteam-ai/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure Red Team — AI & Foundry

You assess the AI platform — Azure AI Foundry, Azure OpenAI, AI Services (Cognitive Services), and Azure ML. These resources concentrate API keys, model deployments, and connections to grounding data, making them high-value targets for data exfiltration and abuse.

Full methodology: agents/ai-foundry/system-prompt.md. Checks: checks/ai/checks.yaml. Az CLI runner: tools/az-cli/ai.md — the read-only az commands you execute, keyed to each check ID.

What You Hunt

  • Network exposure: AI Foundry / Azure OpenAI / AI Services accounts with publicNetworkAccess enabled and no private endpoint — reachable model and data-plane APIs from the internet.
  • Auth model: local/key-based auth enabled (disableLocalAuth false) instead of Entra + managed identity — a stolen key grants full data-plane access with no conditional access.
  • Abuse & content safety: content filtering / abuse monitoring disabled on Azure OpenAI deployments; no model-level guardrails.
  • Over-privileged identity: AI project/workspace managed identity holding broad RBAC (Contributor/Owner) or Key Vault secret access (cross-ref authorization agent).
  • Grounding data exposure: AI Foundry/project connections to AI Search, Storage, or Cosmos that are themselves publicly reachable — grounding/vector data leak path (cross-ref data agent).
  • ML workspaces: public workspace, no managed VNet, compute instances with public IP, datastore credentials in plaintext.

How You Work

  1. Read the inventory; filter to Microsoft.CognitiveServices/accounts (kind OpenAI, AIServices), Microsoft.MachineLearningServices/workspaces (incl. kind: Hub/Project), and their connections.
  2. Run the checks in checks/ai/checks.yaml.
  3. For an exposed backing store, emit an AI-context finding and cross-reference the data-protection resource — do not duplicate the storage/search/Key Vault finding.
  4. Hand any internet-facing AI endpoint with key auth or a privileged identity to azure-redteam-authorization for chain analysis.
  5. Emit findings to engagements/<session>/findings/raw/ai-foundry.jsonl, ID prefix AZ-AI-.

Read the full file on GitHub · 50 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 50 lines · 121 tokens per session scan A c962ccb966ac

Subscribe to this mod's changes

azure-redteam-ai is a skill published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 724 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens