Agent skill · Audited from source

Oura

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

★ 1,425pushed 1 day ago
✕BLOCKGrade D · 69/100 · 6 findings · 19bc863
1,425repo stars · whole vellum-ai/vellum-assistant

Is it safe? No — BLOCK, grade D (69/100). 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 6 findings, 1 critical or high. What it does: Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Oura (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/oura

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 1 critical or high finding, starting with “Prompt injection” in SKILL.md:102. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score69/100✕BLOCK D
1 critical0 high0 medium5 low0 info

BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 642 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 codeNA0
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: critical finding, no behavioural pass, undeclared transfer.

Findings (6)

CRITICALPrompt injectionprompt.transfer_instruction · SKILL.md:102
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
curl -s -X POST "https://api.ouraring.com/oauth/token" \
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine

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/ouraThe 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: Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2

---
name: oura
description: Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "💍"
  vellum:
    category: "health"
    display-name: "Oura Ring"
    includes:
      - oura-setup
---

# Oura Ring — Data Access

Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2.

**For initial setup (OAuth, app registration, token exchange), see the `oura-setup` skill.**

## Prerequisites

- Oura Ring already connected via OAuth (see `oura-setup` skill)
- Credential stored: `oura` / `access_token` with injection template for `api.ouraring.com` (Authorization header, Bearer prefix)
- Credential ID can be found via `assistant credentials list --search oura` (filter for field `access_token`)

## Making Requests

All requests go through the credential proxy — no need to manually attach tokens.

```bash
curl -s "https://api.ouraring.com/v2/usercollection/{endpoint}?start_date=YYYY-MM-DD&end_date=YYYY-MM-DD"
```

Run via `bash` with:

- `network_mode: "proxied"`
- `credential_ids: ["<oura access_token credential_id>"]`

## Endpoints

| Endpoint             | What It Returns                                                          | Best For               |
| -------------------- | ------------------------------------------------------------------------ | ---------------------- |
| `personal_info`      | Age, weight, height, email                                               | Connection test        |
| `daily_sleep`        | Sleep score, duration, efficiency, stages                                | Morning check-in       |
| `sleep`              | Detailed sleep periods — HR, HRV, movement, timestamps                   | Deep sleep analysis    |
| `daily_readiness`    | Readiness score, HRV balance, recovery index                             | Morning readiness      |
| `daily_activity`     | Steps, calories, movement, MET data, activity score                      | Daily activity summary |
| `heartrate`          | Continuous HR readings (uses `start_datetime`/`end_datetime` ISO format) | Workout HR, resting HR |
| `workout`            | Detected workouts — HR, calories, duration, type                         | Exercise tracking      |
| `daily_spo2`         | Blood oxygen (SpO2) nightly average                                      | Breathing/oxygen       |
| `daily_stress`       | Stress score, recovery periods                                           | Stress monitoring      |
| `ring_configuration` | Ring model, firmware, color, design                                      | Ring info              |

## Query Parameters

- **Most endpoints:** `start_date` and `end_date` in `YYYY-MM-DD` format
- **Heart rate:** Uses `start_datetime` and `end_datetime` in ISO 8601 format (e.g. `2025-01-15T00:00:00-05:00`)
- **Personal info / ring config:** No date params needed
- Omitting dates usually returns recent data (last 1-7 days depending on endpoint)

## Common Patterns

### Morning health check

Pull sleep + readiness + activity for today:

```bash
DATE=$(date +%Y-%m-%d)
curl -s "https://api.ouraring.com/v2/usercollection/daily_sleep?start_date=$DATE&end_date=$DATE"
curl -s "https://api.ouraring.com/v2/usercollection/daily_readiness?start_date=$DATE&end_date=$DATE"
```

### Workout details with HR

```bash
YESTERDAY=$(date -v-1d +%Y-%m-%d)
TODAY=$(date +%Y-%m-%d)
curl -s "https://api.ouraring.com/v2/usercollection/workout?start_date=$YESTERDAY&end_date=$TODAY"
```

### Heart rate during a specific window

```bash
# Adjust the datetime range as needed (ISO 8601 with timezone offset)
curl -s "https://api.ouraring.com/v2/usercollection/heartrate?start_datetime=YYYY-MM-DDT23:00:00-05:00&end_datetime=YYYY-MM-DDT01:00:00-05:00"
```

## Notes

- New rings need **1-2 nights** to calibrate before sleep/readiness scores are meaningful
- Sleep data appears a few hours after waking
- Short workouts (<15 min) may not be auto-detected — check raw heart rate instead
- Heart rate endpoint can return large datasets — keep time windows tight
- Rate limit: 5,000 requests per 5 minutes
- Tokens expire after ~30 days. Refresh using the `oura-setup` skill's token refresh instructions.

## Token Refresh

When the access token expires, use the refresh token via the `oura-setup` skill:

```bash
curl -s -X POST "https://api.ouraring.com/oauth/token" \
  -d "grant_type=refresh_token&refresh_token=REFRESH_TOKEN&client_id=CLIENT_ID&client_secret=CLIENT_SECRET"
```

Store the new access_token and refresh_token. See `oura-setup` for full details.

Excerpt, first 4,687 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

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. ✕BLOCK D 69 / 100

    first audit · source 19bc86343b63

README badge

For maintainers · shows the latest audit

ModelsAtlas: BLOCK DMODELSATLASBLOCK · D
[![ModelsAtlas: BLOCK D](https://modelsatlas.com/skills/vellum-ai/oura/badge.svg)](https://modelsatlas.com/skills/vellum-ai/oura/)

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: BLOCK D](https://modelsatlas.com/skills/vellum-ai/oura/badge.svg)](https://modelsatlas.com/skills/vellum-ai/oura/)

Questions about Oura

What does the Oura skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Oura safe to install?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What can Oura 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.