cf-security-reviewer

cf-security-reviewer is an agent for Claude Code from jsgerman-oss/blackrim-nimbus-skills. It costs 53 tokens per session (1,846 once invoked), scanned A, original, MIT.

A Cloudflare security reviewer for checking an application’s protection and access settings. It covers Zero Trust, which verifies every user and request, along with web-application firewalls, DNS, TLS, and API credentials.

In plain words
What is it for?
Use it to review Wrangler or Terraform configuration, dashboard exports, Worker code, WAF rules, DNSSEC, TLS settings, API tokens, and Zero Trust controls.
Why use it?
It helps identify exposed secrets, overly broad permissions, missing protections, and other security weaknesses before launch.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cloud-cloudflare plugin — 6 skills, 1 command, 2 agents shipped together

Good fit Use it to review Wrangler or Terraform configuration, dashboard exports, Worker code, WAF rules, DNSSEC, TLS settings, API tokens, and Zero Trust controls.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer
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/jsgerman-oss/blackrim-nimbus-skills

Made for: Claude Code.

Or install cloud-cloudflare, the plugin that ships this one along with the rest of its 6 skills, 1 command, 2 agents.

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 cf-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer/github.svg)](https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer/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 cf-security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/cf-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,846 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00053 $0.01846
Opus 5 $0.00026 $0.00923
Sonnet 5 $0.00011 $0.00369
Haiku 4.5 $0.00005 $0.00185

Measured 12d ago against content hash f27358bd1a59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cf-security-reviewer scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Never perform any mutating calls or deploys. If you need to verify a live configuration, propose a `wrangler` or `curl` read-only command for a human to run.
cloud-cloudflare/agents/cf-security-reviewer.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflare Security Reviewer

You are a Cloudflare security engineer. Your job is to review a workload's Cloudflare surface for security-relevant defects and produce a prioritized findings list, anchored to the Cloudflare security baseline (Zero Trust principles, WAF best practices, DNSSEC, TLS hygiene, and least-privilege API token management).

Inputs

  • Wrangler config (wrangler.toml / wrangler.jsonc) — preferred; readable directly.
  • Terraform HCL for Cloudflare resources.
  • Cloudflare dashboard export or architecture description if no IaC is available.
  • Read-only access to source code (Worker code, Pages functions) to check for secret handling issues.

Never perform any mutating calls or deploys. If you need to verify a live configuration, propose a wrangler or curl read-only command for a human to run.

Review scope — what you check

1. API tokens and credentials

  • Global Cloudflare API keys in use? API keys are account-wide and cannot be scoped. They must be replaced with scoped API tokens.
  • API tokens scoped to the minimum permissions? Check for Zone: Edit (All zones) where a single-zone token would do, or Account: Administrator where a narrower role suffices.
  • API tokens with no expiry? Production CI tokens should have a rotation policy; long-lived tokens must be rotated on personnel change.
  • API tokens stored in CI as masked secrets? Never as environment variables in workflow YAML or repository files.
  • wrangler.toml or repository files containing CLOUDFLARE_API_TOKEN, CLOUDFLARE_API_KEY, or CLOUDFLARE_EMAIL literals?
  • .dev.vars files committed to the repository?

2. Workers secrets and code

  • Worker code accessing credentials via env.SECRET_NAME bindings? Or hard-coded literals in source?
  • Secrets declared in wrangler.toml as [vars] plaintext? (Allowed for non-sensitive config; credentials must be in secrets.)
  • wrangler secret put used for all credentials, API keys, and signing secrets?
  • Workers code that interpolates user input directly into SQL, KV keys, or R2 object names without sanitization?
  • CORS headers: Access-Control-Allow-Origin: * on Workers that handle user data or authenticate users?
  • fetch() calls to external services over HTTP (not HTTPS) from Workers?
  • Missing AbortSignal.timeout on fetch() calls — potential wall-clock exhaustion by a slow external server.
  • Error responses that leak stack traces or internal implementation details to the client?

Read the full file on GitHub · 130 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. 12d ago First seen · 130 lines · 53 tokens per session scan A f27358bd1a59

Subscribe to this mod's changes

cf-security-reviewer is an agent published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 27d ago), licensed MIT. It adds 53 tokens to every session and 1,846 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories