Agent skill · Audited from source

E2e

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: Run end-to-end tests via the CI workflow.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “E2e (vellum-ai/vellum-assistant)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/vellum-ai/e2e

3 skills are called “E2e”. You are viewing vellum-ai/vellum-assistant.

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/.claude/skills/vellum-skills/e2eThe 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: Run end-to-end tests via the CI workflow.

---
name: e2e
description: >
  Run end-to-end tests via the CI workflow.
---

Run end-to-end tests via the CI workflow.

The user may pass `$ARGUMENTS` to filter to a specific test case by name (e.g., `hello-world`, `phone-setup`). If not provided, infer options from context (see below).

## Steps

### 1. Determine options

**Experimental tests:** Always include `--experimental` by default. The user can pass `--no-experimental` to exclude them.

**Branch detection:** Check what branch you're on via `git branch --show-current`. If you're on a branch other than `main`, automatically pass `-b <branch-name>` so the CI run tests against that branch. The user can override with `-b <other-branch>` explicitly.

**Test case filter:** Determine which test case to target:
1. If the user passes a bare word argument (e.g., `phone-setup`), use that as the filter.
2. Otherwise, look at the conversational context - if you've been working on or discussing a specific e2e test case (e.g., editing `playwright/cases/phone-setup.md`), automatically target that test case.
3. If neither applies, run all tests.

**Additional flags from `$ARGUMENTS`:**
- `--xcode` uses the agent-xcode (AXUIElement) runner
- `-d` or `--detach` triggers the run and exits without polling
- `--no-experimental` overrides the default and excludes experimental tests

### 2. Trigger the CI run

```bash
cd playwright && bun run scripts/agent-ci.ts <options>
```

Map the resolved options:
- Test case filter: `-t <case-name>`
- Experimental (default on): `--experimental`
- Branch: `-b <branch-name>`
- Xcode runner: `--xcode`
- Detach mode: `-d`

Examples:
- `/e2e` (on main, no context) → `bun run scripts/agent-ci.ts --experimental`
- `/e2e` (on branch `feat/phone`, after editing `phone-setup.md`) → `bun run scripts/agent-ci.ts --experimental -b feat/phone -t phone-setup`
- `/e2e hello-world` (on main) → `bun run scripts/agent-ci.ts --experimental -t hello-world`
- `/e2e --detach` (on branch `fix/bug`) → `bun run scripts/agent-ci.ts --experimental -b fix/bug -d`
- `/e2e --no-experimental` → `bun run scripts/agent-ci.ts`

### 3. Report

Before running, briefly state the resolved options (branch, test case, experimental) so the user can see what was inferred.

Once the command finishes (or is dispatched in detach mode), summarize:
- Whether the workflow was triggered successfully
- The branch, test case filter, and flags used
- A link to the running workflow

Excerpt, first 2,445 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/e2e/badge.svg)](https://modelsatlas.com/skills/vellum-ai/e2e/)

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/e2e/badge.svg)](https://modelsatlas.com/skills/vellum-ai/e2e/)

Questions about E2e

What does the E2e skill do?
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Is E2e 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 E2e 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.