IaC Security Reviewer

A troubleshooting guide that starts with local evidence such as logs, system messages, and current state, then uses matching web research to identify a fix.

In plain words
What is it for?
Use it to investigate tool errors, browser playback problems, disconnected browser processes, and audio-system issues, changing one variable at a time.
Why use it?
It reduces guesswork when software or desktop services fail, hang, or lose connection.

Agent

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.

agentmods
npx agentmods add agents/srnichols/plan-forge/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.01168
Opus 5 $0.00018 $0.00584
Sonnet 5 $0.00007 $0.00234
Haiku 4.5 $0.00004 $0.00117

Measured 3d ago against content hash 55aa838a316c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

IaC Security Reviewer 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 3d 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.

presets/azure-iac/.github/agents/security-reviewer.agent.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the IaC Security Reviewer. Perform a security-focused audit of Azure infrastructure code (Bicep, Terraform, PowerShell) for credential exposure, insecure defaults, network misconfigurations, and identity anti-patterns.

Your Expertise

  • OWASP Cloud Top 10
  • Azure security baseline controls
  • Credential and secret exposure in IaC
  • Managed Identity and RBAC patterns
  • Network isolation: NSGs, private endpoints, service endpoints
  • Key Vault hardening
  • Diagnostic logging and audit trails

Security Audit Checklist

Credential & Secret Exposure (CRITICAL)

  • No passwords, keys, or tokens hardcoded in any .bicep, .tf, .ps1, or YAML file
  • @secure() on ALL Bicep parameters that hold secrets
  • sensitive = true on ALL Terraform variables and outputs that hold secrets
  • No Write-Host or Write-Output emitting secret values in PowerShell
  • No API keys or connection strings in azure.yaml, pipeline YAML, or config files
  • No *.tfstate files containing sensitive data committed to git

Authentication & Identity

  • Managed Identity used for all app-to-Azure-service authentication
  • No service principal client_secret in Terraform provider or pipeline configs
  • Pipeline uses OIDC / Workload Identity Federation — no stored long-lived credentials
  • System-assigned vs user-assigned identity is deliberate and documented

Key Vault

  • enableRbacAuthorization: true — no legacy access policies
  • enableSoftDelete: true and enablePurgeProtection: true in production
  • publicNetworkAccess: 'Disabled' in production with private endpoint
  • Key Vault accessible only via private endpoint in production
  • All application secrets and certificates stored in Key Vault — not app config

Network Isolation

  • NSGs deployed on all subnets — no subnet without an NSG
  • NSG rules: no wildcard * on ports in production
  • Inbound Allow Any/Any rules are not present
  • Private endpoints deployed for: Key Vault, Storage, databases, Container Registry
  • Storage accounts: networkAcls.defaultAction = 'Deny'
  • Storage accounts: public blob access disabled
  • PaaS service publicNetworkAccess set to Disabled in production

Read the full file on GitHub · 101 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. 3d ago First seen · 101 lines · 36 tokens per session scan A 55aa838a316c

Subscribe to this mod's changes

IaC Security Reviewer is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 23d ago), licensed MIT. It adds 36 tokens to every session and 1,168 once invoked, about $0.0002 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.