Agent skill · Audited from source

Vellum Heartbeat

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: Configure periodic background checklist runs

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

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

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 codeNA0
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/vellum-heartbeatThe 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: Configure periodic background checklist runs

---
name: vellum-heartbeat
description: Configure periodic background checklist runs
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "💓"
  vellum:
    category: "system"
    display-name: "Heartbeat"
    activation-hints:
      - "Set up a heartbeat, periodic checklist, background health check, or recurring background task"
    avoid-when:
      - "One-off or recurring schedules with specific payloads - use the schedule skill instead"
---

The heartbeat feature runs your `HEARTBEAT.md` checklist periodically in a background conversation. Each run, the assistant works through the checklist and flags anything that needs attention.

## Setup

Edit `config.json` using `file_edit`:

1. **Enable heartbeat**: Set `heartbeat.enabled` to `true`.
2. **Set interval**: Set `heartbeat.intervalMs` (milliseconds between runs, default: 3600000 = 1 hour).
3. **Optional active hours**: Set `heartbeat.activeHoursStart` and `heartbeat.activeHoursEnd` (0-23) to restrict runs to certain hours in the heartbeat timezone. Hours use `heartbeat.timezone` when set, otherwise the user's configured or detected timezone (the host clock is last resort). Both must be set together.

Example config.json heartbeat section:

```json
{
  "heartbeat": {
    "enabled": true,
    "intervalMs": 1800000,
    "activeHoursStart": 8,
    "activeHoursEnd": 22
  }
}
```

Then edit `HEARTBEAT.md` with the checklist items. The assistant will work through this file each heartbeat run.

## Notes

- Toggling `heartbeat.enabled` requires an assistant restart to take effect.
- Changes to `HEARTBEAT.md` take effect on the next heartbeat run (no restart needed).
- The heartbeat runs in a separate background conversation, not the user's active chat.

## Inference

Heartbeat runs use the `heartbeatAgent` call site, which by default resolves to the
`cost-optimized` profile so background checks stay cheap. Override via
`llm.callSites.heartbeatAgent` in workspace config (profile, provider, model,
effort, thinking — whatever the profile supports).

Excerpt, first 2,049 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/vellum-heartbeat/badge.svg)](https://modelsatlas.com/skills/vellum-ai/vellum-heartbeat/)

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

Questions about Vellum Heartbeat

What does the Vellum Heartbeat skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Vellum Heartbeat 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 Vellum Heartbeat 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.