Agent skill · Audited from source

Manage Firewall

skill · microsoft/power-platform-skillsMIT licenceAudited 18 Oct 2026 · source 8075ef5705c5

★ 1,020pushed today
✓SAFEGrade B · 89/100 · 18 Oct 2026 · 8075ef5
1,020repo stars · whole microsoft/power-platform-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 8075ef5705c5 and observed filesystem access and no hard-coded secrets. What it does: Inspects and configures the web application firewall (WAF) in front of a Power Pages production site. Lists the current state, recommends enabling protection when it is off, and walks the user through adding, updating,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Manage Firewall (microsoft/power-platform-skills)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/microsoft/manage-firewall

Trust audit

Audit 0.4.1 · source read 18 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium5 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemDeclared5 observations
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS5
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

LOWFilesystem / pathfs.traversal · scripts/delete-rules.js:10
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} = require('../../../scripts/lib/power-platform-api');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/disable.js:12
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} = require('../../../scripts/lib/power-platform-api');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/enable.js:12
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} = require('../../../scripts/lib/power-platform-api');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/get-rules.js:10
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} = require('../../../scripts/lib/power-platform-api');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · scripts/get-status.js:10
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} = require('../../../scripts/lib/power-platform-api');
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 8075ef5705c5 · 18 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishermicrosoft GitHub organizationOwner of the repository this skill is read from
  • Source foldermicrosoft/power-platform-skills/plugins/power-pages/skills/manage-firewallThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict8075ef5705c5A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Inspects and configures the web application firewall (WAF) in front of a Power Pages production site. Lists the current state, recommends enabling protection when it is off, and walks the user through adding, updating,…

---
name: manage-firewall
description: >-
  Inspects and configures the web application firewall (WAF) in front of a
  Power Pages production site. Lists the current state, recommends enabling
  protection when it is off, and walks the user through adding, updating,
  or removing custom rules — IP blocks, country blocks, path blocks, and
  rate limits. Use when the user wants to turn on WAF, block traffic by
  IP or country, rate-limit login or signup pages, protect pages from
  brute-force attempts, restrict access to specific paths, review the
  current firewall configuration, or asks "is my site protected against
  bots / common web attacks?" — even if they say "add rate limit" or
  "protect login page" without mentioning "firewall" or "WAF".
user-invocable: true
argument-hint: "[optional: --review <out-dir>]"
allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, TaskCreate, TaskUpdate, TaskList
model: opus
---

> **Plugin check**: Run `node "${PLUGIN_ROOT}/scripts/check-version.js"` — if it outputs a message, show it to the user before proceeding.

# Manage Web Application Firewall

Configure the firewall for a Power Pages production site. The firewall is only available on production sites and in supported regions — the scripts detect and report eligibility issues. After rule changes, edge propagation takes up to one hour.

**Initial request:** $ARGUMENTS

## Gotchas

- **Website record id vs portal id.** `.powerpages-site/website.yml` stores the website record id, not the portal id. Every script takes `--portalId`. Resolve once via `website.js --websiteId` during prerequisites.
- **Never resolve by name.** Site names can duplicate; only the website record id is safe.
- **Async operations.** `enable.js` and `disable.js` poll until the status reaches the target value (or timeout). `delete-rules.js` returns immediately (202) — verify via `get-rules.js`.
- **Concurrent-operation guard.** `B003` means another enable/disable is in flight. Poll status until it settles, then retry.
- **False-positive managed rule:** disable via a rule override (`EnabledState: "Disabled"` inside `RuleGroupOverrides` — managed rule fields use PascalCase).
- **First-match-wins.** Rules evaluate in priority order. A geo-allow-then-default-deny pattern requires an explicit default-deny rule AFTER the allow.
- **Custom rule priority range: 11–65000.** Values 1–10 are reserved for platform-managed rules.
- **`set-rules.js` is additive / update-only.** Send only rules being created or modified. The service merges them; existing rules not in the payload are untouched.
- **Use `delete-rules.js` to remove rules.** `set-rules.js` cannot remove. Always use `delete-rules.js --names`.
- **WAF state semantics — `Created` is the only "enabled" state.** `get-status.js` returns `value: "Created"` when the firewall is enabled and actively filtering (counter-intuitive — the API does NOT use `"Enabled"`). Any other value (`Disabled`, `None`, `Enabling`, `Disabling`, `Failed`) means no active policy exists. **MUST** call `get-status.js` first and only invoke `get-rules.js` when `value` is `Created` — otherwise the rules endpoint returns a 500 and the whole firewall section gets skipped in the report.

## Workflow

1. **Prerequisites** — Locate project, confirm sign-in, identify site, check eligibility
2. **Check firewall state** — Capture status and rules
3. **Choose an action** — Context-aware recommendation or question
4. **Apply the change** — Run the matching script, verify
5. **Summarize and next steps** — Present result, record usage, offer follow-ups

## Task Tracking

Create tasks in three groups. Mark each `in_progress` when starting, `completed` when done.

| Group | When to create | Tasks |
|-------|----------------|-------|
| 1 | At start | Check prerequisites |
| 2 | After prerequisites pass | Check firewall state · Choose an action (skip in review mode) |
| 3 | After user confirms an action | Apply the change (skip in review mode OR no change action was chosen) · Summarize and next steps (always) |

---

## 1. Prerequisites

### 1.1 Locate the project, detect review mode

Use `Glob` to find `**/powerpages.config.json`. If `$ARGUMENTS` contains `--review <out-dir>`, remember the output directory — Steps 3–4 are skipped and Step 5 writes JSON only.

### 1.2 Resolve site identifiers

Read `.powerpages-site/website.yml` → extract `id` field → that is `<WEBSITE_ID>`.

If missing, the site has not been deployed. Tell the user and recommend `/deploy-site`. Stop. Do **not** resolve by name or URL.

Resolve to portalId:

```bash
node "${PLUGIN_ROOT}/scripts/website.js" --websiteId "<WEBSITE_ID>"
```

Capture `Id` (portalId), `Type`, `Name`, `WebsiteUrl`. If exit code `2` → sign-in required (`pac auth create` or `az login`). If `null` → site not found in this environment. Stop in either case.

### 1.3 Eligibility

Check the `Type` field and the script responses for eligibility. The scripts return specific error codes for ineligible sites (non-production, unsupported region, restricted feature). Read `references/commands.md` § "Common error catalogue" and § "Regional availability" for the full list.

If the site is ineligible, tell the user in plain language what the limitation is and stop.

---

## 2. Check firewall state

### 2.1 Get status (always run first)

```bash
node "${PLUGIN_ROOT}/skills/manage-firewall/scripts/get-status.js" --portalId "<PORTAL_ID>"
```

The response shape is `{ "status": "ok", "value": "<state>" }`.

- `Created` — WAF is enabled and filtering. Proceed to **2.2** to fetch rules.
- Any other value (`Disabled`, `None`, `Enabling`, `Disabling`, `Failed`, etc.) — **WAF is not enabled**. **MUST NOT** call `get-rules.js` — the rules endpoint will return a 500 because no active policy exists to read. Skip **2.2** and treat the rules payload as empty: `{ "status": "ok", "body": { "CustomRules": [], "ManagedRules": [] } }`.

If the status response is `"status": "unsupported"`, tell the user the fire

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 8075ef5

Download folder ↗
git clone https://github.com/microsoft/power-platform-skills
git -C power-platform-skills checkout 8075ef5705c5

The author documents no install command, so this uses the repository directly. Our verdict covers commit 8075ef5705c5 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 8075ef5705c5

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/microsoft/manage-firewall/badge.svg)](https://modelsatlas.com/skills/microsoft/manage-firewall/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/microsoft/manage-firewall/badge.svg)](https://modelsatlas.com/skills/microsoft/manage-firewall/)

Questions about Manage Firewall

What does the Manage Firewall skill do?
A plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.
Is Manage Firewall safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Manage Firewall access on my machine?
The audit observed that it reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
How current is this page?
The grade is for one exact copy of the source (8075ef5705c5), read on 2026-10-18. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.