Agent skill · Audited from source

Sentry App Setup

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

★ 1,425pushed 1 day ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? Yes — SAFE, 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. What it does: Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Sentry App Setup (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/sentry-app-setup

Trust audit

Audit 0.4.1 · source read 14 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

  • 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 codePASS0
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)

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/sentry-app-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: Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity

---
name: sentry-app-setup
description: Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity
compatibility: "Designed for Vellum personal assistants"
metadata:
  icon: assets/icon.svg
  emoji: "🔺"
  vellum:
    category: "development"
    display-name: "Sentry App Setup"
    user-invocable: true
---

## Overview

Set up a **Sentry internal integration** so the assistant can interact with a Sentry organization — querying issues, resolving events, managing releases, and monitoring alerts as its own entity.

Internal integrations are scoped to a single organization. They don't require an OAuth flow — you get an auth token immediately after creation. Tokens don't expire automatically (but can be revoked manually).

**Total manual effort: ~2 interactions** — create the integration and grab the auth token.

## Prerequisites

- User must be an **organization owner or manager** in Sentry
- User must be logged into Sentry in their browser

## Setup Flow

### Step 0: Check Existing Configuration

Before starting, check whether Sentry is already configured by running the check script:

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

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

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

### Step 1: Create the Internal Integration

Direct the user to create a new internal integration:

> Open **https://sentry.io/settings/developer-settings/new-internal/** to create a new internal integration.

Guide them through the form:

| Field           | Value                                                                |
| --------------- | -------------------------------------------------------------------- |
| **Name**        | The assistant's name. This is how the integration appears in Sentry. |
| **Webhook URL** | Leave blank (not needed for API-only usage)                          |

**Permissions** — set these based on what the assistant needs. Recommended defaults:

| Resource          | Access Level |
| ----------------- | ------------ |
| **Issue & Event** | Read         |
| **Project**       | Read         |
| **Organization**  | Read         |

Adjust permissions up or down based on the user's needs. The principle of least privilege applies — only request what you'll actually use. Add write access to Issue & Event or Project if the assistant needs to resolve issues or manage releases.

> Click **Save Changes** when done. The integration is automatically installed on the organization.

### Step 2: Collect the Auth Token

After saving, Sentry displays the integration's details page. An auth token is automatically generated.

Tell the user: on the integration details page, find the **Tokens** section and copy the auth token.

Then run the store script to securely collect and store the token:

```bash
bun skills/sentry-app-setup/scripts/store-token.ts
```

The script opens a secure credential prompt in the user's app, stores the token in the encrypted vault with the correct injection templates, and exits. No further action needed — if it exits 0, the token 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.

### Step 3: Collect the Organization Slug

The org slug is needed for API calls. Ask the user for it — it's visible in their Sentry URL as `sentry.io/organizations/{slug}/`.

Remember the org slug for future API calls.

### Step 4: Verify

After storing the token, verify the connection:

```bash
curl -s https://sentry.io/api/0/organizations/{org_slug}/ \
  -H "Content-Type: application/json"
```

Run with `network_mode: "proxied"` and the sentry credential. A successful response returns the organization's details.

If the response returns a 401, the token is invalid or revoked. If 403, the integration doesn't have `org:read` permission.

### Step 5: Set the Integration Logo (Optional)

Sentry supports uploading a logo for internal integrations through the web UI (not via API).

Direct the user:

> Go to **Settings > Developer Settings**, find your integration, and upload a logo.

**Logo** requirements: PNG, 256×256 to 1024×1024, transparent background (unless the logo fills the entire space).

**Small Icon** requirements (optional, separate upload): PNG, must use **only black with an alpha channel** — no colors, no white fill. Sentry rejects icons that use any color other than black.

### Step 6: Report Success

Summarize with the completed checklist:

"Setup complete!
✅ Internal integration created
✅ Auth token configured
✅ Connection verified
{logo_line}

Connected: {integration_name} in {org_slug}
Permissions: {list the configured permission levels}
Token: does not expire (can be revoked in Settings > Developer Settings)"

For `{logo_line}`:

- If logo was uploaded: `✅ Logo uploaded`
- If skipped: `⬜ Logo — upload anytime in Settings > Developer Settings`

Excerpt, first 5,200 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. ✓SAFE B 89 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/vellum-ai/sentry-app-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/sentry-app-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: SAFE B](https://modelsatlas.com/skills/vellum-ai/sentry-app-setup/badge.svg)](https://modelsatlas.com/skills/vellum-ai/sentry-app-setup/)

Questions about Sentry App Setup

What does the Sentry App 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 Sentry App Setup 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 Sentry App Setup 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.