Screen Recording

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

Gates applied: no behavioural pass.

assistant/CLAUDE.md

assistant/src/approvals/CLAUDE.md

assistant/src/notifications/CLAUDE.md

assistant/src/runtime/CLAUDE.md

gateway/CLAUDE.md

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

• Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
• Source foldervellum-ai/vellum-assistant/skills/screen-recordingThe 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

Its description: Record the user's screen as a video file

---
name: screen-recording
description: Record the user's screen as a video file
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "🎬"
  vellum:
    platforms:
      - macos
    category: "content"
    display-name: "Screen Recording"
---

Capture screen recordings as video files attached to the conversation.

## Activation

The user asks to start, stop, pause, resume, or restart a screen recording.
Routing does not depend on matching phrases: see Routing below.

## Routing

Recording is managed through dedicated HTTP endpoints (`/v1/recordings/*`) rather than text-based intent detection. Two routing mechanisms exist:

### 1. `commandIntent` (structured command) - highest priority

The macOS client can send structured intents with `domain: 'screen_recording'` and `action: 'start' | 'stop' | 'restart' | 'pause' | 'resume'`. These bypass text parsing entirely. The assistant checks for `commandIntent` before any text analysis.

### 2. HTTP endpoints

Clients call the recording HTTP endpoints directly:

- `POST /v1/recordings/start` - start a screen recording
- `POST /v1/recordings/stop` - stop the active recording
- `POST /v1/recordings/pause` - pause the active recording
- `POST /v1/recordings/resume` - resume a paused recording
- `GET /v1/recordings/status` - get current recording status
- `POST /v1/recordings/status` - recording lifecycle callback from the client

### 3. Normal processing

If no recording intent is detected, the message flows to the classifier and computer-use session as usual.

## Behavior Rules

1. **Do not invoke computer use** for recording-only requests. The assistant handles these directly.
2. **One recording at a time.** If a recording is already active, starting another returns an "already recording" message.
3. **Conversation-linked.** Each recording is linked to the conversation that started it for attachment purposes. However, since only one recording can be active at a time, stop commands from any conversation will stop the active recording regardless of which conversation started it.
4. **Permission required.** Screen recording requires macOS Screen Recording permission. If denied, the user sees actionable guidance to enable it in System Settings.
5. **Mixed-intent prompts** (recording + other task) are NOT intercepted by the standalone route - the recording action is deferred and executed alongside the task.
6. **Restart always reopens the source picker** and requires source reselection.
7. **Restart cancel** (user closes the source picker) leaves state idle - no false "recording started" message.
8. **Pause/resume toggle the recording** without stopping it. The HUD shows paused state.

## What This Skill Does NOT Do

- This skill does not contain recorder logic - the `RecordingManager` and `ScreenRecorder` in the macOS app handle the actual recording.
- This skill does not provide shell commands or scripts for recording.
- This skill does not fall back to computer use for recording tasks.
- This skill does not handle informational questions about recording - those flow through to normal AI response.

Excerpt, first 3,113 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.

git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 19bc86343b63

Questions about Screen Recording

• github.com/vellum-ai/vellum-assistant/tree/main/skills/screen-re — the audited source at commit 19bc86343b63 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology