Agent skill · Audited from source
Update
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 found no filesystem, network or shell access and no hard-coded secrets. What it does: Restart the Vellum assistant and gateway services. Smart branch handling: pulls from main by default, restarts in-place on feature branches, or switches to a specified branch. Pass --pull to force-pull on the current…
Cite
Cite this page
ModelsAtlas. “Update (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/update
2 skills are called “Update”. You are viewing vellum-ai/vellum-assistant.
- vellum-ai/vellum-assistant★ 1.4k✓SAFE
- davepoon/buildwithclaude★ 3.6k✓SAFE
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
- 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
| 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 | NA | 0 |
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 (5)
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
- —
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/.claude/skills/updateThe 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: Restart the Vellum assistant and gateway services. Smart branch handling: pulls from main by default, restarts in-place on feature branches, or switches to a specified branch. Pass --pull to force-pull on the current…
---
name: update
description: >
Restart the Vellum assistant and gateway services. Smart branch handling: pulls from main by default, restarts in-place on feature branches, or switches to a specified branch. Pass --pull to force-pull on the current branch.
---
# Update - Restart Vellum (with Smart Branch Handling)
Restart the Vellum assistant and gateway services with branch-aware git behavior.
## Arguments
The user may pass `$ARGUMENTS` to control branch behavior:
| Invocation | Behavior |
|---|---|
| `/update` (no args, on `main`) | Pull latest from `origin/main` (default) |
| `/update` (no args, on a feature branch) | Skip git ops - restart with the current checkout |
| `/update <branch>` | Check out that branch, pull if it has a remote |
| `/update --pull` | Force pull on whatever branch you're currently on |
## Steps
0. Ensure Bun is on PATH:
```bash
export PATH="$HOME/.bun/bin:$PATH"
```
1. Preflight snapshot - capture current state before making changes:
```bash
vellum ps
```
2. Quiesce with `vellum sleep` - stop assistant and gateway processes. This is directory-agnostic and stops processes globally regardless of CWD:
```bash
vellum sleep || true
```
3. Verify stopped - run `vellum ps` and confirm no running processes. If `vellum ps` shows processes still running, run fallback cleanup to force-kill them:
```bash
vellum ps
```
**Fallback cleanup if `vellum ps` confirms processes are still running:**
```bash
pkill -x "vellum-assistant" || true
pkill -f "gateway/src/index" || true
lsof -ti :7830 | xargs kill -9 2>/dev/null || true
lsof -ti :7821 | xargs kill -9 2>/dev/null || true
```
After fallback cleanup, run `vellum ps` again to confirm all processes are stopped.
4. Smart branch handling - determine what git operations (if any) to perform:
```bash
CURRENT=$(git branch --show-current)
GIT_OPS_RAN=false
```
**Case A - `--pull` flag:** Force pull on the current branch.
```bash
if [[ "$ARGUMENTS" == "--pull" ]]; then
git pull
GIT_OPS_RAN=true
fi
```
**Case B - Explicit branch name provided:** Check out the requested branch, pulling if possible. Before checking out, verify the working tree is clean - if there are uncommitted changes, **stop and warn the user** rather than silently losing work. Do NOT stash automatically.
```bash
if [[ -n "$ARGUMENTS" && "$ARGUMENTS" != "--pull" ]]; then
if ! git diff --quiet || ! git diff --cached --quiet; then
echo "ERROR: Uncommitted changes detected. Commit or stash them before switching branches."
# Stop and report the error to the user. Do not proceed.
fi
git checkout "$ARGUMENTS"
git pull origin "$ARGUMENTS" 2>/dev/null || true
GIT_OPS_RAN=true
fi
```
**Case C - No args, on `main`:** Pull latest from origin (preserves current default behavior).
```bash
if [[ -z "$ARGUMENTS" && "$CURRENT" == "main" ]]; then
git pull origin main
GIT_OPS_RAN=true
fi
```
**Case D - No args, on a feature branch:** Skip git ops entirely - just restart with the current checkout.
```bash
if [[ -z "$ARGUMENTS" && "$CURRENT" != "main" ]]; then
echo "On branch '$CURRENT' - skipping git pull, restarting with current checkout"
fi
```
5. Install dependencies - only if git operations ran (dependencies are unlikely to have changed for a local-only restart):
```bash
if [[ "$GIT_OPS_RAN" == "true" ]]; then
cd assistant && bun install && cd ..
cd gateway && bun install && cd ..
fi
```
6. Restart with `vellum wake` - start assistant and gateway from the current checkout. `vellum wake` must be run from the checkout directory that should supply the new assistant code:
```bash
vellum wake
```
7. Verify fresh state - run `vellum ps` to confirm processes are running:
```bash
sleep 5
echo ""
echo "=== Startup Summary ==="
vellum ps
echo "======================="
```
## Report
Tailor the report to what actually happened:
- **If git pulled (Cases A, B, C):** Report what was pulled (new commits), the branch, and whether dependencies were updated.
- **If restarted in-place (Case D):** Report that services were restarted on the current branch with no git changes.
- **Always include:** The startup summary block output (assistant health, gateway health).Excerpt, first 4,397 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/update/)
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/update/)
<a href="https://modelsatlas.com/skills/vellum-ai/update/"><img src="https://modelsatlas.com/skills/vellum-ai/update/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about Update
What does the Update skill do?
Is Update safe to install?
What can Update access on my machine?
How current is this page?
Sources
- github.com/vellum-ai/vellum-assistant/tree/main/.claude/skills/u — 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 Update skill do?
- Is Update safe to install?
- What can Update access on my machine?