agentmods.dev

firewall-zone-policy-audit

firewall-zone-policy-audit is a skill for Claude Code from swkstudios/unifi-fabric-mcp-server. It costs 37 tokens per session (780 once invoked), scanned A, original, MIT.

A read-first workflow for checking UniFi firewall zones and policies, where zones describe network areas such as internal and external networks. It can also change the order of policies within one zone pair after approval.

In plain words
What is it for?
Use it to audit firewall rules, identify WAN-to-LAN access, and reorder policies for a UniFi zone pair.
Why use it?
It helps find potentially unsafe external-to-internal allow rules without assuming a rule name is safe. It also shows the exact ordering change before applying it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the unifi-fabric plugin — 6 skills shipped together

not rated 6repo +1 4d ago A scan 37 tokens original MIT

Good fit Use it to audit firewall rules, identify WAN-to-LAN access, and reorder policies for a UniFi zone pair.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit
View source ↗ swkstudios/unifi-fabric-mcp-server
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.

Any agent
npx skills add swkstudios/unifi-fabric-mcp-server --skill firewall-zone-policy-audit
Clone the repo
git clone --depth 1 https://github.com/swkstudios/unifi-fabric-mcp-server

Made for: Claude Code.

Or install unifi-fabric, the plugin that ships this one along with the rest of its 6 skills.

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 firewall-zone-policy-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit/github.svg)](https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit)
Your own site
<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit/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 firewall-zone-policy-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit"><img src="https://agentmods.dev/badge/skills/swkstudios/unifi-fabric-mcp-server/firewall-zone-policy-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 780 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 $0.00037 $0.00780
Opus 5.5 $0.00015 $0.00312
Sonnet 5.5 $0.00007 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 2d ago against content hash 777df9cb83fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

firewall-zone-policy-audit 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 2d 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.

plugins/claude/skills/firewall-zone-policy-audit/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Firewall and zone-based policy audit

Read first; write only the change the operator approved. In discovery mode (the default) run each tool below through call_read_tool or call_write_tool with name and arguments; in full mode call it directly. For anything else use search_tools and describe_tool.

  1. Call list_firewall_zones_proxy with {"host":"<console>","site":"<site>"} and map zone names (case-insensitive: Internal, External, ...) to data[].id.
  2. Call list_firewall_policies with the same scope; omit offset and limit to get every page. Check source and destination zones, action, enabled state and origin. Flag every External-to-Internal allow; never infer safety from a policy name.
  3. For each zone pair with policies, call get_firewall_policy_ordering with host, site, source_zone_id and destination_zone_id; keep the body as returned.
  4. Report zones, policies, effective order and suspected WAN-to-LAN allows; missing data is unknown, not safe. For a change, show the exact before and after ordering.
  5. After approval, call set_firewall_policy_ordering with the same zone pair and the whole read-back object, reordered, as ordering (both arrays, [] for an empty side, no index field). It has no per-call preview, so the ordering shown in step 4 is the preview; a status: "dry_run" result means the server runs in dry-run mode and nothing changed.
  6. Re-read get_firewall_policy_ordering and compare it with the approval. On a mismatch stop and report; never retry by guessing.

Tool contracts checked against code (paths under src/unifi_fabric/)

Tool Mode Required arguments (optional) Return shape and source
list_firewall_zones_proxy read host, site (offset, limit, filter) {data, totalCount}, all pages; server.py::list_firewall_zones_proxy → tools/firewall_proxy.py::list_firewall_zones; readOnlyHint: true
list_firewall_policies read host, site (offset, limit, filter) {data, totalCount}, all pages; server.py::list_firewall_policies → tools/firewall_proxy.py::list_firewall_policies; readOnlyHint: true
get_firewall_policy_ordering read host, site, source_zone_id, destination_zone_id {orderedFirewallPolicyIds: {beforeSystemDefined, afterSystemDefined}} verbatim; server.py::get_firewall_policy_ordering → tools/firewall_proxy.py::get_firewall_policy_ordering; readOnlyHint: true
set_firewall_policy_ordering write host, site, source_zone_id, destination_zone_id, ordering upstream body verbatim, or {status, dryRun, message, preview}; server.py::set_firewall_policy_ordering → tools/firewall_proxy.py::set_firewall_policy_ordering; readOnlyHint: false

Read the full file on GitHub · 38 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. 2d ago First seen · 38 lines · 37 tokens per session scan A 777df9cb83fc

Subscribe to this mod's changes

firewall-zone-policy-audit is a skill published in the GitHub repository swkstudios/unifi-fabric-mcp-server (6 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 780 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-04.

Hardware and IoTSecurityfastmcpmcpnetwork-automationubiquitiunifi
Related

firewall-zone-policy-audit compared with skills from other repositories

firewall-zone-policy-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
firewall-zone-policy-auditswkstudios/unifi-fabric-mcp-serverSkill64d agoMITA37Claude Code
unifi-protectsirkirby/unifi-mcpSkill1.0kyesterdayMITA112Claude Code
unifi-accesssirkirby/unifi-mcpSkill1.0kyesterdayMITA70Claude Code
network-health-checksirkirby/unifi-mcpSkill1.0kyesterdayMITA49Claude Code
percepxion-oobautomateyournetwork/netclawSkill715yesterdayApache-2.0A70Claude Code
unifi-networksirkirby/unifi-mcpSkill1.0kyesterdayMITA83Claude Code
unifi-access-supportsirkirby/unifi-mcpSkill1.0kyesterdayMITA31Claude Code