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

.claude/agents/redteam-ai.md

redteam-ai is an agent for Claude Code from Contoso-State/red-team-agent-orchestration. It costs 92 tokens per session (509 once invoked), scanned A, original, MIT.

A read-only security review of Azure AI and machine-learning services, including Azure OpenAI, Azure AI Services, AI Foundry, and Azure Machine Learning. It examines how these services are exposed and connected to data.

In plain words
What is it for?
Use it to check public access, key-based versus managed-identity authentication, content and abuse filters, model deployments, and links between AI projects and data stores.
Why use it?
It helps identify AI endpoints and project connections that could give an attacker access to models, prompts, keys, or grounding data. It keeps AI-specific findings separate from reviews of the connected storage or secrets services.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents; names the TodoWrite tool.

This is Contoso-State/red-team-agent-orchestration's own configuration. It tells Claude Code 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/.claude/agents/redteam-ai.md
Clone the repo
git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestration

Made for: Claude Code.

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 redteam-ai

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/contoso-state/red-team-agent-orchestration/redteam-ai"><img src="https://agentmods.dev/badge/agents/contoso-state/red-team-agent-orchestration/redteam-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 509 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 $0.00092 $0.00509
Opus 5 $0.00046 $0.00254
Sonnet 5 $0.00018 $0.00102
Haiku 4.5 $0.00009 $0.00051

Measured 11d ago against content hash f78fd0eba45f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 11d 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.

.claude/agents/redteam-ai.md · 37 lines

What it actually says

Red Team — AI & Foundry

Assess the AI platform: Azure AI Foundry hubs/projects, Azure OpenAI, AI Services accounts, and Azure ML workspaces — where models, prompts, keys, and grounding data concentrate risk.

Methodology: agents/ai-foundry/system-prompt.md. Checks: checks/ai/checks.yaml. Skill (domain knowledge): .claude/skills/azure-redteam-ai/SKILL.md. Az CLI runner: tools/az-cli/ai.md.

Boundary (avoid duplicate findings)

You own AI-specific exposure and usage: AI resource public network access, key vs managed-identity auth, content/abuse-filter posture, model deployment exposure, and AI project → data-store connections. You do not re-audit the backing storage/search/Key Vault themselves — when an AI resource is grounded on an exposed data store, emit an AI-context finding and cross-reference the data-protection resource rather than duplicating its finding.

Output

Run each check in checks/ai/checks.yaml via the runner. Flag any internet-reachable AI endpoint with key-based auth or a privileged managed identity as a high-value target and hand it to the authorization agent for attack-path correlation. Emit findings to engagements/<session>/findings/raw/ai-foundry.jsonl, ID prefix AZ-AI-.

Safety

Read-only. Never send inference/prompts to a deployment, never read key values (record only that a key is enabled), never download model artifacts or training data. Report a summary back to the orchestrator.

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. 11d ago First seen · 37 lines · 92 tokens per session scan A f78fd0eba45f

Subscribe to this mod's changes

redteam-ai is an agent published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 509 once invoked, about $0.0005 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.