Agent skill · Audited from source

Google Workspace Cli

skill · borghei/Claude-SkillsNOASSERTION licenceAudited 19 Oct 2026 · source 6e3fcbdbb5cf

★ 949pushed 12 days agoversion 1.0.0
!CAUTIONGrade B · 89/100 · 6 findings · 6e3fcbd
949repo stars · whole borghei/Claude-Skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6e3fcbdbb5cf and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 6 findings, 0 critical or high. What it does: This skill should be used when the user asks to "audit Google Workspace", "check GWS security settings", "set up Google Workspace authentication", "diagnose Workspace issues", or "review Google admin configurations".

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Google Workspace Cli (borghei/Claude-Skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/borghei/google-workspace-cli

2 skills are called “Google Workspace Cli”. You are viewing borghei/Claude-Skills.

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high5 medium0 low1 info

CAUTION means the audit found things worth knowing before you trust this skill. 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, activityWARN5
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (6)

INFOPrompt injectionprompt.authority_framing · references/gws-admin-guide.md:108
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
1. **Super Admin** - Full access (limit to 2-3 accounts)
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherborghei GitHub userOwner of the repository this skill is read from
  • Source folderborghei/Claude-Skills/engineering/google-workspace-cliThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
  • Repository statusNot archivedLast push 12 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: This skill should be used when the user asks to "audit Google Workspace", "check GWS security settings", "set up Google Workspace authentication", "diagnose Workspace issues", or "review Google admin configurations".

---
name: google-workspace-cli
description: >
  This skill should be used when the user asks to "audit Google Workspace",
  "check GWS security settings", "set up Google Workspace authentication",
  "diagnose Workspace issues", or "review Google admin configurations".
license: MIT + Commons Clause
metadata:
  version: 1.0.0
  author: borghei
  category: engineering
  domain: google-workspace
  updated: 2026-04-02
  tags: [google-workspace, gws, admin, security, audit]
---
# Google Workspace CLI

> **Category:** Engineering
> **Domain:** Google Workspace Administration

## Overview

The **Google Workspace CLI** skill provides tools for auditing Google Workspace configurations, generating authentication setup documentation, and diagnosing common GWS issues. It helps IT administrators maintain secure, well-configured Workspace environments without needing to navigate complex admin consoles.

## Clarify First

Before running, confirm these inputs. If any is unknown or vague, ASK — do not assume:

- [ ] **Task** — security audit, auth setup guide, or diagnostics (selects `workspace_audit.py` vs `auth_setup_guide.py` vs `gws_doctor.py`)
- [ ] **Config export or auth method** — the GWS config JSON to audit, or the auth method and scopes for a setup guide (sets `--config` or `--method`/`--scopes`)
- [ ] **Output mode** — human-readable vs JSON for automation (sets `--format json`)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

## Quick Start

```bash
# Audit Workspace security configuration
python scripts/workspace_audit.py --config gws-config.json

# Generate auth setup guide
python scripts/auth_setup_guide.py --method oauth --scopes admin,drive

# Run diagnostics
python scripts/gws_doctor.py --check all

# JSON output for automation
python scripts/workspace_audit.py --config gws-config.json --format json
```

## Tools Overview

### workspace_audit.py

Audits Google Workspace configuration exports for security best practices.

| Feature | Description |
|---------|-------------|
| 2FA enforcement | Checks if 2-step verification is required |
| Password policy | Validates password strength requirements |
| Sharing settings | Reviews external sharing configurations |
| App access | Checks third-party app access policies |
| Admin roles | Reviews admin role assignments |
| Mobile management | Checks device management policies |
| Drive settings | Validates Drive sharing and access controls |

### auth_setup_guide.py

Generates step-by-step authentication setup documentation for GWS API access.

| Feature | Description |
|---------|-------------|
| OAuth setup | Generates OAuth 2.0 configuration guide |
| Service account | Creates service account setup documentation |
| API scopes | Lists required scopes for each API |
| Domain delegation | Documents domain-wide delegation setup |
| Testing guide | Provides verification steps |

### gws_doctor.py

Diagnostic tool for common Google Workspace configuration issues.

| Feature | Description |
|---------|-------------|
| DNS checks | Validates MX, SPF, DKIM, DMARC records format |
| SSL/TLS | Checks certificate and transport security settings |
| Integration health | Validates common integration patterns |
| Config consistency | Checks for conflicting settings |
| Best practices | Compares against GWS recommended settings |

## Workflows

### Security Audit Workflow

1. **Export config** - Export GWS settings to JSON via Admin SDK or manual export
2. **Audit** - Run workspace_audit.py against the config file
3. **Review findings** - Prioritize critical security gaps
4. **Remediate** - Apply recommended settings in Admin Console
5. **Re-audit** - Verify changes resolved findings

### API Setup Workflow

1. **Plan** - Determine which APIs and scopes are needed
2. **Generate guide** - Run auth_setup_guide.py with desired method
3. **Follow steps** - Create credentials in Google Cloud Console
4. **Configure** - Set up domain delegation if needed
5. **Verify** - Test API access with provided verification steps

### Health Check Workflow

1. **Run diagnostics** - Execute gws_doctor.py with all checks
2. **Review results** - Check DNS, email, and integration health
3. **Fix issues** - Address failures in priority order
4. **Re-check** - Verify fixes pass diagnostics

### Regular Maintenance

```bash
# Monthly security audit
python scripts/workspace_audit.py --config gws-export.json --format json > audit_$(date +%Y%m).json

# Weekly health check
python scripts/gws_doctor.py --check dns,email --format json
```

## Reference Documentation

- [GWS Admin Guide](references/gws-admin-guide.md) - Security settings, API configuration, DNS requirements

## Common Patterns Quick Reference

### Security Priorities
| Setting | Priority | Impact |
|---------|----------|--------|
| 2FA enforcement | Critical | Prevents account takeover |
| Password policy | Critical | Reduces credential attacks |
| External sharing | High | Prevents data leakage |
| App access control | High | Limits third-party risk |
| Mobile management | Medium | Secures device access |
| Admin role review | Medium | Limits privilege exposure |

### DNS Records for Email
| Record | Purpose | Example |
|--------|---------|---------|
| MX | Email routing | `ASPMX.L.GOOGLE.COM` |
| SPF | Sender verification | `v=spf1 include:_spf.google.com ~all` |
| DKIM | Email signing | Domain-specific CNAME |
| DMARC | Policy enforcement | `v=DMARC1; p=reject; rua=mailto:...` |

### API Scopes
| API | Scope | Purpose |
|-----|-------|---------|
| Admin SDK | `admin.directory.user` | User management |
| Drive | `drive.readonly` | File listing |
| Gmail | `gmail.settings.basic` | Email settings |
| Calendar | `calendar.readonly` | Calendar access |

### Common Issues
| Issue | Symptom | Fix |
|-------|---------|-----|
| No 2FA | Account takeover risk | Enable 2FA enforcement |
| Weak passwords | Credential stuffing | 

Excerpt, first 6,000 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 6e3fcbd

Download folder ↗
git clone https://github.com/borghei/Claude-Skills
git -C Claude-Skills checkout 6e3fcbdbb5cf

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6e3fcbdbb5cf 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. !CAUTION B 89 / 100

    first audit · source 6e3fcbdbb5cf

A11y Audit!CAUTION

borghei/Claude-Skills

This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".

★ 949Grade B
Agent Designer!CAUTION

borghei/Claude-Skills

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent…

★ 949Grade B
Agent Protocol!CAUTION

borghei/Claude-Skills

Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.

★ 949Grade B
Agent Workflow Designer!CAUTION

borghei/Claude-Skills

Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant…

★ 949Grade B
Agenthub!CAUTION

borghei/Claude-Skills

Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to…

★ 949Grade B
Analytics Engineer!CAUTION

borghei/Claude-Skills

Analytics engineering across data modeling, dbt, transformation, and semantic layers. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, or optimizing warehouse…

★ 949Grade B

Questions about Google Workspace Cli

What does the Google Workspace Cli skill do?
385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Is Google Workspace Cli safe to install?
With care. The audit graded it B (89/100) and found 6 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Google Workspace Cli 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 (6e3fcbdbb5cf), read on 2026-10-19. 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.