redteam-web

redteam-web is a cursor rule for Cursor from Contoso-State/red-team-agent-orchestration. It costs 83 tokens per session (485 once invoked), scanned A, original, MIT.

Rules for an Azure security agent that checks how websites, APIs, and static files are exposed to the internet.

In plain words
What is it for?
Use them to assess Azure Static Web Apps, storage websites, Front Door, CDN, Application Gateway, and API Management exposure.
Why use it?
They provide a defined review boundary for finding weak web firewalls, TLS settings, redirects, public endpoints, and exposed API gateways.

Cursor rule for Cursor

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

Good fit Use them to assess Azure Static Web Apps, storage websites, Front Door, CDN, Application Gateway, and API Management exposure.

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

README.md
[![agentmods](https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-web.svg)](https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-web)
Your own site
<a href="https://agentmods.dev/rules/contoso-state/red-team-agent-orchestration/redteam-web"><img src="https://agentmods.dev/badge/rules/contoso-state/red-team-agent-orchestration/redteam-web.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 485 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 $0.00083 $0.00485
Opus 5 $0.00042 $0.00243
Sonnet 5 $0.00017 $0.00097
Haiku 4.5 $0.00008 $0.00049

Measured 4d ago against content hash 819ef3750e8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

redteam-web 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 4d 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-web.mdc · 35 lines

What it actually says

Red Team — Web & Static Sites

Assess the web delivery edge: how content and APIs are published to the internet — Static Web Apps, Storage static websites, Front Door / CDN, Application Gateway WAF, and API Management.

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

Boundary (avoid duplicate findings)

You own the web edge / delivery posture: WAF presence and mode, TLS/HTTPS-only, custom-domain binding, public static endpoints, and APIM gateway exposure. You do not own: Azure network primitives (public IPs, NSGs, firewalls) — that is network-exposure; nor App Service/Functions auth and managed-identity hardening — that is compute-platform. For storage static-website hosting you assess the web exposure angle and cross-reference the data-protection finding on the storage account itself.

Output

Run each check in checks/web/checks.yaml via the runner. Flag any internet-facing web edge with no WAF or weak TLS, and hand exposed unauthenticated endpoints to the authorization agent for attack-path correlation. Emit findings to engagements/<session>/findings/raw/web-exposure.jsonl, ID prefix AZ-WEB-.

Safety

Read-only. Never send attack traffic, crawl, fuzz, or probe the live sites — assess configuration only. 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. 4d ago First seen · 35 lines · 83 tokens per session scan A 819ef3750e8f

Subscribe to this mod's changes

redteam-web is a cursor rule published in the GitHub repository Contoso-State/red-team-agent-orchestration (6 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 485 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 2026-09-03.