Agent skill · Audited from source
Contacts
skill · vellum-ai/vellum-assistantMIT licenceAudited 14 Oct 2026 · source 19bc86343b63
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
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
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
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 5 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 5 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (10)
LOWInventory / provenanceinv.symlink · assistant/CLAUDE.md
assistant/CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · assistant/src/approvals/CLAUDE.md
assistant/src/approvals/CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · assistant/src/notifications/CLAUDE.md
assistant/src/notifications/CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · assistant/src/runtime/CLAUDE.md
assistant/src/runtime/CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWInventory / provenanceinv.symlink · gateway/CLAUDE.md
gateway/CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:3
import { cliIpcCall } from "../../../../ipc/cli-client.js";- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:4
import { resolveGuardianName } from "../../../../prompts/user-reference.js";- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:5
import { throwIfCancelled } from "../../../../tools/shared/abort.js";- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · tools/contact-merge.ts:9
} from "../../../../tools/types.js";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · tools/contact-search.ts:3
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 channelsExcerpt, 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
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
- ✓SAFE B 89 / 100
first audit · source
19bc86343b63
README badge
For maintainers · shows the latest audit
[](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.
Similar skills
All coding & review skills →vellum-ai/vellum-assistant
Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol
vellum-ai/vellum-assistant
Shop on Amazon and Amazon Fresh through your browser
vellum-ai/vellum-assistant
Record and analyze API surfaces of web services
vellum-ai/vellum-assistant
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill…
vellum-ai/vellum-assistant
Drive a specific named macOS app via raw input bypassing the Accessibility tree
vellum-ai/vellum-assistant
Import conversation history from ChatGPT into Vellum
Add this badge to your README
[](https://modelsatlas.com/skills/vellum-ai/contacts/)
<a href="https://modelsatlas.com/skills/vellum-ai/contacts/"><img src="https://modelsatlas.com/skills/vellum-ai/contacts/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about Contacts
What does the Contacts skill do?
Is Contacts safe to install?
What can Contacts access on my machine?
How current is this page?
Sources
- github.com/vellum-ai/vellum-assistant/tree/main/assistant/src/co — the audited source at commit 19bc86343b63 and every finding aboveObserved · 14 Oct 2026
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.
- What does the Contacts skill do?
- Is Contacts safe to install?
- What can Contacts access on my machine?