Agent skill · Audited from source

Public Ingress

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

★ 1,425pushed 1 day ago
!CAUTIONGrade B · 89/100 · 10 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 found no filesystem, network or shell access and no hard-coded secrets. The audit raised 10 findings, 0 critical or high. What it does: Set up and manage ngrok-based public ingress for local assistants; do not use this in managed mode when platform callback routing is available

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Public Ingress (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/public-ingress

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high5 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
  • 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, activityPASS5
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA5
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 (10)

MEDIUMNetwork egressnet.raw_ip · SKILL.md:52
F-04 Network egressCWE-200 · CWE-319Layer L1
The local gateway URL is available as the `$INTERNAL_GATEWAY_BASE_URL` environment variable (defaults to `http://127.0.0.1:7830`).
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · SKILL.md:59
F-04 Network egressCWE-200 · CWE-319Layer L1
If `publicBaseUrl` is already set and the tunnel is running (check via `curl -s http://127.0.0.1:4040/api/tunnels`), tell the user the current status and ask if they want to reconfigure or if this is
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · SKILL.md:64
F-04 Network egressCWE-200 · CWE-319Layer L1
Invoke-RestMethod http://127.0.0.1:4040/api/tunnels
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · SKILL.md:147
F-04 Network egressCWE-200 · CWE-319Layer L1
curl -s http://127.0.0.1:4040/api/tunnels 2>/dev/null
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · SKILL.md:153
F-04 Network egressCWE-200 · CWE-319Layer L1
Invoke-RestMethod http://127.0.0.1:4040/api/tunnels -ErrorAction SilentlyContinue
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/public-ingressThe 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 manage ngrok-based public ingress for local assistants; do not use this in managed mode when platform callback routing is available

---
name: public-ingress
description: Set up and manage ngrok-based public ingress for local assistants; do not use this in managed mode when platform callback routing is available
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "🌍"
  vellum:
    category: "system"
    display-name: "Public Ingress"
    activation-hints:
      - "Local assistant needs a public webhook or OAuth callback URL"
      - "ngrok tunnel setup for a non-managed assistant"
    avoid-when:
      - "Running in a platform-managed assistant with platform callback routing available"
---

You are setting up and managing a public ingress tunnel so that external services (Telegram webhooks, OAuth callbacks, etc.) can reach the local Vellum gateway. This skill uses ngrok to create a secure tunnel and persists the public URL as `ingress.publicBaseUrl`.

If managed platform callback routing is available, stop and do not continue with ngrok. In platform-managed deployments, Telegram/Twilio/OAuth callback routing should use the platform callback route flow instead of local public ingress.

## Overview

The Vellum gateway listens locally and needs a publicly reachable URL for:

- Telegram webhook delivery
- Google/Slack OAuth redirect callbacks
- Any other inbound webhook traffic

This skill installs ngrok, configures authentication, starts a tunnel, discovers the public URL, and saves it to the assistant's ingress config.

On Windows, use the PowerShell blocks instead of the POSIX ones.

## Step 0: Reject Managed Callback Environments

Check whether managed platform callback routing is available:

```bash
assistant platform status --json
```

If the result shows `isPlatform: true` and `available: true`, stop here. Tell the user that this assistant should use the platform callback route flow instead of ngrok, and do not install or start ngrok.

## Step 1: Check Current Ingress Status

First, check whether ingress is already configured:

```bash
assistant config get ingress.publicBaseUrl
assistant config get ingress.enabled
```

The local gateway URL is available as the `$INTERNAL_GATEWAY_BASE_URL` environment variable (defaults to `http://127.0.0.1:7830`).

The commands return:

- `ingress.publicBaseUrl` - currently configured public ingress URL (if any)
- `ingress.enabled` - whether ingress is enabled

If `publicBaseUrl` is already set and the tunnel is running (check via `curl -s http://127.0.0.1:4040/api/tunnels`), tell the user the current status and ask if they want to reconfigure or if this is sufficient.

On Windows, check the tunnel with:

```powershell
Invoke-RestMethod http://127.0.0.1:4040/api/tunnels
```

## Step 2: Install ngrok

Check if ngrok is installed:

```bash
ngrok version
```

If not installed, install it:

**macOS (Homebrew):**

```bash
brew install ngrok/ngrok/ngrok
```

**Windows (Microsoft Store via WinGet):**

```powershell
winget install ngrok -s msstore
```

**Linux (snap):**

```bash
sudo snap install ngrok
```

**Linux (apt - alternative):**

```bash
curl -sSL https://ngrok-agent.s3.amazonaws.com/ngrok.asc | sudo tee /etc/apt/trusted.gpg.d/ngrok.asc >/dev/null
echo "deb https://ngrok-agent.s3.amazonaws.com buster main" | sudo tee /etc/apt/sources.list.d/ngrok.list
sudo apt update && sudo apt install ngrok
```

After installation, verify with `ngrok version`.

## Step 3: Authenticate ngrok

Check if ngrok already has an auth token configured:

```bash
ngrok config check
```

If not authenticated:

1. Tell the user: "You need an ngrok account to create tunnels. If you don't have one, sign up at https://dashboard.ngrok.com/signup - it's free."
2. Once they have an account, run `assistant credentials prompt` (via the bash tool) to securely collect their auth token. **Never ask the user to paste the token directly in chat.**

   ```bash
   assistant credentials prompt --service ngrok --field authtoken \
     --label "ngrok Auth Token" \
     --description "Get your auth token from https://dashboard.ngrok.com/get-started/your-authtoken" \
     --usage-description "ngrok authentication token for creating public tunnels"
   ```

3. Once the credential is stored, reveal it and apply it to ngrok:

   ```bash
   ngrok config add-authtoken "$(assistant credentials reveal --service ngrok --field authtoken)"
   ```

   On Windows:

   ```powershell
   $token = assistant credentials reveal --service ngrok --field authtoken
   ngrok config add-authtoken $token
   ```

   If no value is returned, re-run `assistant credentials prompt` and try again.

Verify authentication succeeded by checking `ngrok config check` again.

## Step 4: Start the Tunnel

Before starting, check for an existing ngrok process to avoid duplicates:

```bash
curl -s http://127.0.0.1:4040/api/tunnels 2>/dev/null
```

On Windows:

```powershell
Invoke-RestMethod http://127.0.0.1:4040/api/tunnels -ErrorAction SilentlyContinue
```

If a tunnel is already running, check whether it points to the correct local target. If so, skip to Step 5. If it points elsewhere, stop it first:

```bash
pkill -f ngrok || true
sleep 1
```

On Windows:

```powershell
Get-Process ngrok -ErrorAction SilentlyContinue | Stop-Process
Start-Sleep -Seconds 1
```

Start ngrok in the background tunneling to the local gateway URL:

```bash
nohup ngrok http "$INTERNAL_GATEWAY_BASE_URL" --log=stdout > /tmp/ngrok.log 2>&1 &
echo $! > /tmp/ngrok.pid
```

On Windows:

```powershell
$logPath = Join-Path $env:TEMP "ngrok.log"
$errorLogPath = Join-Path $env:TEMP "ngrok-error.log"
Start-Process ngrok -ArgumentList @("http", $env:INTERNAL_GATEWAY_BASE_URL, "--log=stdout") -RedirectStandardOutput $logPath -RedirectStandardError $errorLogPath -WindowStyle Hidden
```

Wait a few seconds for the tunnel to establish.

## Step 4b: Verify Port Alignment

Before discovering the public URL, verify that ngrok is forwarding to the same port the gateway is actually listening on. A mismatch here causes silent failures - webhooks appear to be delivered but never reach the

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/public-ingress/badge.svg)](https://modelsatlas.com/skills/vellum-ai/public-ingress/)

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/public-ingress/badge.svg)](https://modelsatlas.com/skills/vellum-ai/public-ingress/)

Questions about Public Ingress

What does the Public Ingress skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Public Ingress safe to install?
With care. The audit graded it B (89/100) and found 10 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Public Ingress access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
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.