redteam-compute

redteam-compute is a cursor rule for Cursor from Contoso-State/red-team-agent-orchestration. It costs 85 tokens per session (420 once invoked), scanned A, original, MIT.

A read-only security review of Azure virtual machines, virtual machine scale sets, App Service, and Functions, which run applications without requiring you to manage all the underlying servers.

In plain words
What is it for?
It checks compute configuration and flags internet-facing systems with privileged managed identities, while leaving containers and Kubernetes to a separate review.
Why use it?
It helps identify weak encryption, exposed identities or secrets, unsafe remote access features, FTP, debugging exposure, and missing application authentication.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

Good fit It checks compute configuration and flags internet-facing systems with privileged managed identities, while leaving containers and Kubernetes to a separate review.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/contoso-state/red-team-agent-orchestration/redteam-compute
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Contoso-State/red-team-agent-orchestration

Made for: Cursor.

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-compute

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-compute"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-compute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 420 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 $0.00085 $0.00420
Opus 5 $0.00043 $0.00210
Sonnet 5 $0.00017 $0.00084
Haiku 4.5 $0.00009 $0.00042

Measured 9d ago against content hash ac1982e23cff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

redteam-compute 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 9d 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.

.cursor/rules/redteam-compute.mdc · 32 lines

What it actually says

Red Team — Compute Platform

Assess the machines and serverless apps that run code and hold managed identities — VMs/VMSS, App Service, and Functions. Containers and Kubernetes (AKS, ACR, Container Apps/Instances) belong to the Azure Container & Kubernetes Agent — defer those.

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

Output

Run each check in checks/compute/checks.yaml via the runner. Flag any privileged managed identity on internet-facing compute as a high-value pivot and note it for the authorization agent. Emit findings to engagements/<session>/findings/raw/compute-platform.jsonl, ID prefix AZ-COMP-.

Boundary

If the inventory contains Microsoft.ContainerService, Microsoft.ContainerRegistry, Microsoft.App, or Microsoft.ContainerInstance, leave them to the Azure Container & Kubernetes Agent (checks/container/checks.yaml) — do not re-derive cluster/registry config.

Safety

Read-only. Never exec into VMs, never use run-command. 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. 9d ago First seen · 32 lines · 85 tokens per session scan A ac1982e23cff

Subscribe to this mod's changes

redteam-compute is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 420 once invoked, about $0.0004 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.