Agent skill · Audited from source

build-zoom-bot

skill · anthropics/knowledge-work-pluginsApache-2.0 licenceAudited 28 Oct 2026 · source fbc0c4cf804e

★ 33,567pushed today
✓SAFEGrade B · 89/100 · 28 Oct 2026 · fbc0c4c
33,567repo stars · whole anthropics/knowledge-work-plugins

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit fbc0c4cf804e and found no filesystem, network or shell access and no hard-coded secrets. What it does: Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “build-zoom-bot (anthropics/knowledge-work-plugins)”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/anthropics/build-zoom-bot

Trust audit

Audit 0.4.1 · source read 28 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 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, activityPASS0
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 (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha fbc0c4cf804e · 28 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheranthropics GitHub organizationOwner of the repository this skill is read from
  • Source folderanthropics/knowledge-work-plugins/partner-built/zoom-plugin/skills/build-zoom-botThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictfbc0c4cf804eA new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.

---
name: build-zoom-bot
description: Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.
---

# /build-zoom-bot

Use this skill for automation that joins meetings, captures media, or reacts to live session data.

## Covers

- Bot architecture
- Meeting join strategy
- Real-time media and transcript handling
- Backend orchestration
- Storage, post-processing, and event flow design

## Workflow

1. Clarify whether the bot needs to join, observe, transcribe, summarize, or act.
2. Route to Meeting SDK and RTMS as the core implementation path.
3. Add REST API for meeting/resource management and Webhooks for asynchronous events when needed.
4. Call out environment and lifecycle constraints early.

## Primary References

- [meeting-sdk](../meeting-sdk/SKILL.md)
- [rtms](../rtms/SKILL.md)
- [scribe](../scribe/SKILL.md)
- [rest-api](../rest-api/SKILL.md)
- [webhooks](../webhooks/SKILL.md)

## Common Mistakes

- Treating batch transcription and live media as the same workflow
- Designing the bot before defining join authority and auth model
- Forgetting post-meeting storage and retry behavior

Excerpt, first 1,249 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 fbc0c4c

Download folder ↗
git clone https://github.com/anthropics/knowledge-work-plugins
git -C knowledge-work-plugins checkout fbc0c4cf804e

The author documents no install command, so this uses the repository directly. Our verdict covers commit fbc0c4cf804e 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 fbc0c4cf804e

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/build-zoom-bot/badge.svg)](https://modelsatlas.com/skills/anthropics/build-zoom-bot/)

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/anthropics/build-zoom-bot/badge.svg)](https://modelsatlas.com/skills/anthropics/build-zoom-bot/)

Questions about build-zoom-bot

What does the build-zoom-bot skill do?
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
Is build-zoom-bot 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 build-zoom-bot 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 (fbc0c4cf804e), read on 2026-10-28. 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.