Agent skill · Audited from source

Mailgun Setup

skill · vellum-ai/vellum-assistantMIT licenceAudited 14 Oct 2026 · source 19bc86343b63

★ 1,425pushed 1 day ago
!CAUTIONGrade B · 89/100 · 7 findings · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 19bc86343b63 and observed network access and no hard-coded secrets. The audit raised 7 findings, 1 critical or high. What it does: Set up and send emails via a user-provided Mailgun account (BYO email provider)

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Mailgun Setup (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/mailgun-setup

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100!CAUTION B
0 critical1 high1 medium5 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared1 observation
  • 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, activityPASS5
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN1
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (7)

HIGHPrompt injectionprompt.credential_read · SKILL.md:35
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Run the store script to securely collect the API key:
Why
asks the agent to read credentials
Fix
—
MEDIUMNetwork egressnet.beacon_words · scripts/setup-webhook.ts:75
F-04 Network egressCWE-200 · CWE-319Layer L1
callbackUrl = data.callbackUrl || data.url || data.callback_url;
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
  • Source foldervellum-ai/vellum-assistant/skills/mailgun-setupThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Set up and send emails via a user-provided Mailgun account (BYO email provider)

---
name: mailgun-setup
description: Set up and send emails via a user-provided Mailgun account (BYO email provider)
compatibility: "Designed for Vellum personal assistants"
metadata:
  icon: assets/icon.svg
  emoji: "📬"
  vellum:
    category: "email"
    display-name: "Mailgun Email Setup"
    user-invocable: true
---

## Overview

Send emails through the user's own Mailgun account. The user provides their Mailgun API key and domain, and you send via their infrastructure.

## Setup

### Step 0: Check Existing Configuration

Before starting, check whether Mailgun is already configured:

```bash
bun skills/mailgun-setup/scripts/check-config.ts
```

The script outputs JSON: `{ "configured": boolean, "hasApiKey": boolean, "hasWebhookKey": boolean, "details": string }`.

- If `configured` is `true` — Mailgun is already set up. Offer to verify the connection or reconfigure.
- If `configured` is `false` — continue to Step 1.

### Step 1: Store the API Key

Run the store script to securely collect the API key:

```bash
bun skills/mailgun-setup/scripts/store-api-key.ts
```

The script opens a secure credential prompt, stores the key, and exits. If it exits 0, the key is stored. Exit code **130** means the user cancelled the prompt — nothing was stored; that's a valid choice, not an error, so ask whether they'd like to try again rather than treating it as a failure. Any other non-zero exit is a real failure. **Never ask for the key in chat.**

**Note:** Mailgun uses HTTP Basic Auth with username `api` and the API key as the password. The credential proxy cannot construct Basic Auth headers automatically. Instead, use `curl -u "api:$KEY"` in bash commands — retrieve the key from the vault at runtime. See the sending examples below.

### Step 2: Detect the Domain

After storing the API key, **automatically detect the user's domain** — don't ask them for it. Retrieve the API key from the vault and call the Mailgun Domains API:

```bash
curl -s --user "api:$MAILGUN_API_KEY" \
  https://api.mailgun.net/v4/domains?state=active
```

The response contains an `items` array of domain objects with `name` and `state` fields. Pick the first domain with `"state": "active"`. If no active domains are found, try the EU endpoint (`https://api.eu.mailgun.net/v4/domains?state=active`). If still none, tell the user they need to verify a domain in their Mailgun dashboard first.

Use `hi@<domain>` as the default sender address. Remember the domain and region (US/EU) for future sends.

### Step 3: Verify the Connection

Confirm the API key works by checking the domain response returned in Step 2. A successful response (HTTP 200) with domain data confirms the connection.

### Step 4: Webhook Setup (for receiving email)

If the user also wants to **receive** emails via Mailgun, run the webhook setup script:

```bash
bun skills/mailgun-setup/scripts/setup-webhook.ts --domain "<verified domain>" [--region eu]
```

This script:

1. Registers a callback URL via the webhooks system
2. Creates an inbound route in Mailgun via their API
3. Prompts the user for their webhook signing key (found in the Mailgun dashboard: **Settings > API Security > HTTP Webhook Signing Key**)

If the script fails because no public base URL is configured (self-hosted only), load the `public-ingress` skill to walk the user through setting one up, then retry.

### Step 5: Report Success

Summarize with the completed checklist:

"Setup complete!
✅ API key configured
✅ Domain detected: `<domain>` (region: US/EU)
✅ Connection verified
{webhook_line}

Default sender: hi@`<domain>`"

For `{webhook_line}`:

- If webhook was set up: `✅ Inbound route and webhook signing key configured`
- If skipped: `⬜ Webhook — run setup again to enable inbound email`

## Sending Email

Use `bash` with `curl` to call the Mailgun API. Pass the API key via `-u` for Basic Auth:

```bash
curl -s --user "api:$MAILGUN_API_KEY" \
  https://api.mailgun.net/v3/DOMAIN/messages \
  -F from="Name <[email protected]>" \
  -F to="[email protected]" \
  -F subject="Hello" \
  -F text="Plain text body" \
  -F html="<p>HTML body</p>"
```

Replace `DOMAIN` with the user's Mailgun sending domain.

### API Parameters

| Parameter       | Type   | Required | Description                                   |
| --------------- | ------ | -------- | --------------------------------------------- |
| `from`          | string | ✅       | Sender address (`"Name <email>"` format)      |
| `to`            | string | ✅       | Recipient(s), comma-separated for multiple    |
| `subject`       | string | ✅       | Email subject                                 |
| `text`          | string |          | Plain text body                               |
| `html`          | string |          | HTML body                                     |
| `cc`            | string |          | CC recipients, comma-separated                |
| `bcc`           | string |          | BCC recipients, comma-separated               |
| `h:Reply-To`    | string |          | Reply-to address                              |
| `h:In-Reply-To` | string |          | Message-ID of parent (for threading)          |
| `h:References`  | string |          | Space-separated chain of ancestor Message-IDs |

### Threading (replies)

To reply in a thread, include custom headers:

```bash
curl -s --user "api:$MAILGUN_API_KEY" \
  https://api.mailgun.net/v3/DOMAIN/messages \
  -F from="[email protected]" \
  -F to="[email protected]" \
  -F subject="Re: Original subject" \
  -F text="Reply body" \
  -F "h:In-Reply-To=<original-message-id>" \
  -F "h:References=<original-message-id>"
```

### Response

Success returns `{ "id": "<message-id>", "message": "Queued. Thank you." }` with HTTP 200.

Errors return `{ "message": "error description" }` with 4xx/5xx status.

### Regions

Mailgun has US and EU regions:

- **US (default):** `https://api.mailgun.net/v3/DOMAIN/messages`
- **EU:** `https://api.eu.mailgun.net/v3/DOMAIN/messages`

Ask the user which regi

Excerpt, first 6,001 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 19bc863

Download folder ↗
git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

The author documents no install command, so this uses the repository directly. Our verdict covers commit 19bc86343b63 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. !CAUTION B 89 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/vellum-ai/mailgun-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/mailgun-setup/)

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

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/vellum-ai/mailgun-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/mailgun-setup/)

Questions about Mailgun Setup

What does the Mailgun Setup skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Mailgun Setup safe to install?
With care. The audit graded it B (89/100) and found 7 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Mailgun Setup access on my machine?
The audit observed that it reaches the network. 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 (19bc86343b63), read on 2026-10-14. 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.