Agent skill · Audited from source

Contacts

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 observed filesystem access and no hard-coded secrets. What it does: Manage contacts, communication channels, access control, and invite links

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

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

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium10 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

  • FilesystemUndeclared5 observations, not in its own description
  • 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 codePASS5
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)

LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:3
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { cliIpcCall } from "../../../../ipc/cli-client.js";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:4
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { resolveGuardianName } from "../../../../prompts/user-reference.js";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:5
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { throwIfCancelled } from "../../../../tools/shared/abort.js";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:9
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
} from "../../../../tools/types.js";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · tools/contact-search.ts:3
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { cliIpcCall } from "../../../../ipc/cli-client.js";
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/assistant/src/config/bundled-skills/contactsThe 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: Manage contacts, communication channels, access control, and invite links

---
name: contacts
description: Manage contacts, communication channels, access control, and invite links
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "👥"
  vellum:
    display-name: "Contacts"
    category: "productivity"
    activation-hints:
      - "Look up contact info before asking the user for email addresses or phone numbers"
      - "User wants to manage who can message the assistant, or create/revoke invite links"
---

Manage the user's contacts, relationship graph, access control (trusted contacts), and invite links. This skill covers contact CRUD with multi-channel tracking, controlling who can message the assistant through external channels (Telegram, phone), and creating/managing invite links that grant access.

## Contact Management

> **Every contact write goes through the guardian.** You can list and search contacts on your own. To create, edit, delete, merge, or bind a channel to one, run the matching command below: each opens a form in the guardian's app, and the write happens only if they submit it. You are proposing, not writing. Say so: "I'll put that up for you to confirm," not "Done."
>
> Two things a contact record does **not** do: it grants no access (a record has no channels, so nobody can message the assistant through it), and it is not a channel. Use `assistant contacts channels add <contact_id>` to bind an address to a contact that already exists, or `assistant contacts invites create` to let someone bind their own.
>
> The form needs the guardian's desktop or web app to be open. If a command reports that it timed out, nobody answered: tell the user, and do not retry in a loop.
>
> One exception you must not take: the `contact_merge` tool writes immediately, with no confirmation. Use `assistant contacts merge` instead, so the guardian sees what is being combined before the donor record is deleted.
>
> A form the guardian closes without answering is not a failure. The command prints `Cancelled: nothing was written`, exits 130, and writes nothing. Report that as "the guardian did not confirm", not as an error, and do not retry in a loop.

### Create a contact

```bash
assistant contacts create --name "Alice" --json
```

Opens an add-contact form prefilled with what you pass. The guardian can edit the name and notes before submitting, so treat the result as theirs, not yours: read the command's output rather than assuming the values you proposed were the ones written.

Optional flags:

- `--notes` -- proposed notes, prefilled into the form
- `--channel` -- also bind a channel on the same form (`email`, `phone`, `telegram`, `whatsapp`, `slack`). Requires `--name`.
- `--address` -- address to pre-fill for that channel; the guardian can edit it before submitting. Requires `--channel`.
- `--verify` -- pre-check the form's "mark verified" box. Requires `--channel`.
- `--label` / `--description` -- what the form says about why you are asking
- `--timeout` -- how long the form stays open, in ms (default 300000)

With `--channel`, the record and the channel are one form and one guardian confirmation:

```bash
assistant contacts create --name "Alice" --channel email --address "[email protected]" --json
```

`--name` is required in that mode, because the contact is created under it. The form shows `--notes` but does not let the guardian edit them, so they are written as passed; use `assistant contacts update` to change them afterwards. `--address` and `--verify` each need `--channel`, so either one without it is refused rather than ignored.

The `--json` shape follows the mode: without `--channel` it is `{ok, contact}`, so the new id is `contact.id`; with `--channel` it is the address form's `{ok, contactId, channelId, channelType, address, verified}`, so the id is `contactId`. Read the right one before passing it to `contacts invites create --contact-id`.

Use this before creating an invite for someone who is not in the contact graph yet.

### Bind a channel to an existing contact

```bash
assistant contacts channels add "<contact_id>" --channel email --address "[email protected]" --json
```

Opens an address form naming that contact, so the guardian can see where the channel is going. Whatever address they submit binds to that contact: one confirmation, and no second record. This is how you add an address to somebody who is already in the graph. `--channel` is required.

Optional flags:

- `--address` -- address to pre-fill; the guardian can edit it before submitting
- `--verify` -- pre-check the form's "mark verified" box. The guardian decides: unchecked, the channel stays unverified and cannot message the assistant.
- `--label` / `--description` -- what the form says about why you are asking
- `--timeout` -- how long the form stays open, in ms (default 300000)

Two contacts cannot share one address. An address held by a different contact when the form is submitted is refused, the refusal names that contact, and nothing is written. Passing `--address` also checks up front and warns when the address looks taken, without refusing.

For an address that belongs to nobody yet, `assistant contacts prompt` is the create-or-bind path:

```bash
assistant contacts prompt --channel email --json
assistant contacts prompt --contact-id "<contact_id>" --channel email --json
```

On its own it looks up the `(channel type, address)` pair the guardian submits: a match reuses that contact and channel, and no match creates a new contact named after the address. `--contact-id` targets an existing contact instead, the same bind `channels add` does under its own verb.

### Update a contact

```bash
assistant contacts update "<contact_id>" --name "Alice Chen" --json
assistant contacts update "<contact_id>" --notes "Moved to Berlin" --json
```

Opens an edit form showing the current name next to the proposed change. At least one of `--name` or `--notes` is required. This edits the record only. To revoke or block someone's access, use `assistant contacts channels

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

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

Questions about Contacts

What does the Contacts skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is Contacts 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 Contacts access on my machine?
The audit observed that it reads or writes files. At least one of those is not mentioned in its own description, which is itself a finding. 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.