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.
npx skills add vinayaklatthe/microsoft-security-skills --skill azure-wafgit clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skillsWrote 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.
[](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-waf)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-waf"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/azure-waf/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.
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-waf"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/azure-waf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00219 | $0.02071 |
| Opus 5 | $0.00110 | $0.01035 |
| Sonnet 5 | $0.00044 | $0.00414 |
| Haiku 4.5 | $0.00022 | $0.00207 |
Grade A, and why
azure-waf 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Web Application Firewall (WAF)
Azure WAF is an OWASP-aligned application-layer firewall available in two host services:
- Azure Front Door (Premium / Standard) — global, anycast, edge-tier, ideal for internet-facing apps and APIs that benefit from edge presence and built-in caching.
- Azure Application Gateway (WAF v2) — regional, integrated with backend pools, ideal for app-internal or VNet-bound workloads that already terminate on App Gateway.
When to use
Protecting public web applications and APIs from layer-7 attacks: SQLi, XSS, RCE patterns, automated scanners, credential stuffing, scraping, and bot abuse. Use this skill for host selection, policy authoring, exclusion tuning, and operational ownership.
Do not use this skill for layer 3/4 DDoS (azure-ddos-protection), east-west /
non-HTTP traffic (azure-firewall), or non-HTTP protocols.
Pick the host
| Host | Best for |
|---|---|
| Front Door Premium WAF | Internet apps/APIs needing global edge, advanced bot manager, JS/JSON challenges, private-link backends |
| Front Door Standard WAF | Cost-sensitive internet apps with managed Default Rule Set + custom rules |
| App Gateway WAF v2 | Regional apps already on App Gateway, VNet-internal apps, bring-your-own-cert/zonal needs |
Rule of thumb: Internet-facing new build → Front Door Premium. Brownfield with existing App Gateway + sticky reasons → App Gateway WAF.
Approach
-
Start in Detection (audit) mode. Always. Two minimum weeks of production traffic (more for seasonal apps) before flipping to Prevention.
-
Apply Microsoft's Default Rule Set (DRS). Current generation is preferred over the older OWASP CRS for new deployments. Enable Bot Manager rule set on Premium for Front Door.
-
Authentication-aware rules first.
- Rate limit anonymous endpoints (login, search, signup) — typical 100/min/IP for login.
- Geo-block countries you don't serve, but allowlist VPN concentrators or partner regions.
- JSON / JS challenge on suspicious bot scores (Premium) — silently filters headless browsers.
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.
- 12d ago First seen · 146 lines · 219 tokens per session scan A 299211cf10da
azure-waf is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 219 tokens to every session and 2,071 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
agents-sdk-provision
Use when provisioning Azure resources for a Microsoft Agents SDK application — including creating an Azure Bot Service resource, setting up Entra app registrations, configuring identity credentials (UserManagedIdentity, FederatedCredentials, or ClientSecret), adding a Teams channel, running Bicep deployments for SSO…
detecting-azure-service-principal-abuse
Detect and investigate Azure service principal abuse including privilege escalation, credential compromise, admin consent bypass, and unauthorized enumeration in Microsoft Entra ID environments.
detecting-azure-lateral-movement
Detect lateral movement in Azure AD/Entra ID environments using Microsoft Graph API audit logs, Azure Sentinel KQL hunting queries, and sign-in anomaly correlation to identify privilege escalation, token theft, and cross-tenant pivoting.
aspire
Build, upgrade, and operate Aspire 13.5.x C# or TypeScript application hosts with the current CLI, AppHost, ServiceDefaults, integrations, dashboard, testing, MCP, and deployment patterns for distributed apps. USE FOR: Aspire.AppHost.Sdk, Aspire.Hosting., DistributedApplication.CreateBuilder, apphost.mts…
azure-functions
Build, review, or migrate Azure Functions in .NET with correct execution model, isolated worker setup, bindings, DI, and Durable Functions patterns. USE FOR: working on Azure Functions in .NET; migrating from the in-process model to the isolated worker model; adding Durable Functions, bindings, or host configuration.…