Agent skill · Audited from source

gws-docs

skill · googleworkspace/cliApache-2.0 licenceAudited 29 Oct 2026 · source bcdfbd3e9abf

★ 31,973pushed 2 days agoversion 0.22.5
✓SAFEGrade B · 89/100 · 29 Oct 2026 · bcdfbd3
31,973repo stars · whole googleworkspace/cli

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit bcdfbd3e9abf and found no filesystem, network or shell access and no hard-coded secrets. What it does: Read and write Google Docs.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “gws-docs (googleworkspace/cli)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/googleworkspace/gws-docs

Trust audit

Audit 0.4.1 · source read 29 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 bcdfbd3e9abf · 29 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishergoogleworkspace GitHub organizationOwner of the repository this skill is read from
  • Source foldergoogleworkspace/cli/skills/gws-docsThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictbcdfbd3e9abfA new audit runs when the source changes
  • Repository statusNot archivedLast push 2 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Read and write Google Docs.

---
name: gws-docs
description: "Read and write Google Docs."
metadata:
  version: 0.22.5
  openclaw:
    category: "productivity"
    requires:
      bins:
        - gws
    cliHelp: "gws docs --help"
---

# docs (v1)

> **PREREQUISITE:** Read `../gws-shared/SKILL.md` for auth, global flags, and security rules. If missing, run `gws generate-skills` to create it.

```bash
gws docs <resource> <method> [flags]
```

## Helper Commands

| Command | Description |
|---------|-------------|
| [`+write`](../gws-docs-write/SKILL.md) | Append text to a document |

## API Resources

### documents

  - `batchUpdate` — Applies one or more updates to the document. Each request is validated before being applied. If any request is not valid, then the entire request will fail and nothing will be applied. Some requests have replies to give you some information about how they are applied. Other requests do not need to return information; these each return an empty reply. The order of replies matches that of the requests.
  - `create` — Creates a blank document using the title given in the request. Other fields in the request, including any provided content, are ignored. Returns the created document.
  - `get` — Gets the latest version of the specified document.

## Discovering Commands

Before calling any API method, inspect it:

```bash
# Browse resources and methods
gws docs --help

# Inspect a method's required params, types, and defaults
gws schema docs.<resource>.<method>
```

Use `gws schema` output to build your `--params` and `--json` flags.

Excerpt, first 1,556 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 bcdfbd3

Download folder ↗
git clone https://github.com/googleworkspace/cli
git -C cli checkout bcdfbd3e9abf

The author documents no install command, so this uses the repository directly. Our verdict covers commit bcdfbd3e9abf only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source bcdfbd3e9abf

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/googleworkspace/gws-docs/badge.svg)](https://modelsatlas.com/skills/googleworkspace/gws-docs/)

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/googleworkspace/gws-docs/badge.svg)](https://modelsatlas.com/skills/googleworkspace/gws-docs/)

Questions about gws-docs

What does the gws-docs skill do?
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Is gws-docs 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 gws-docs access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does gws-docs work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (bcdfbd3e9abf), read on 2026-10-29. 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.