Google Workspace
NousResearch/hermes-agent
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python. An agent skill from NousResearch/hermes-agent.
Agent skill
Hardens a Google Workspace tenant via Admin Console configuration: phishing-resistant MFA enforcement, DLP policies, email authentication (SPF/DKIM/DMARC), OAuth third-party app control, and…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-security --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .claude/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .claude/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-securityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-security --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .agents/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .agents/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-security --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .cursor/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .cursor/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/implementing-google-workspace-admin-security--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-security --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .gemini/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .gemini/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-securityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .github/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .github/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-google-workspace-admin-security --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/implementing-google-workspace-admin-security .opencode/skills/implementing-google-workspace-admin-security && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "implementing-google-workspace-admin-security" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-google-workspace-admin-security into .opencode/skills/implementing-google-workspace-admin-security/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-google-workspace-admin-security", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
implementing-google-workspace-admin-securityHardens a Google Workspace tenant via Admin Console configuration: phishing-resistant MFA enforcement, DLP policies, email authentication (SPF/DKIM/DMARC), OAuth third-party app control, and…
Implementing Google Workspace Admin Security is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Hardens a Google Workspace tenant via Admin Console configuration: phishing-resistant MFA enforcement, DLP policies, email authentication (SPF/DKIM/DMARC), OAuth third-party app control, and external sharing restrictions. Use when hardening a Google Workspace or G Suite tenant, enforcing MFA and OAuth app controls, or configuring cloud office security administration.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).
It sits in Documents & Office, covering Cloud office suites. It works with Google Workspace. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
opensslFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
siem.corp.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SECURITY_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Implementing Google Workspace Admin Security loads about 4.3k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 615 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 615 words, ~4,317 tokens.
.claude/skills/implementing-google-workspace-admin-security/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Do not use for Microsoft 365 environments; Google Workspace has distinct admin console settings and API configurations that differ from Azure AD/Entra ID controls.
Secure the highest-privilege accounts in the Google Workspace tenant:
# Google Workspace Admin SDK - configure admin account security
# Using gam (Google Apps Manager) CLI tool
# List all super admin accounts for audit
gam print admins role "Super Admin" > super_admins.csv
echo "Review and minimize super admin count (recommended: 2-3 maximum)"
# Enforce Advanced Protection Program for super admins
# APP provides strongest account protections:
# - Requires FIDO2 security key for sign-in
# - Blocks third-party app access to Gmail and Drive
# - Enhanced account recovery verification
gam update user superadmin@corp.com \
advanced_protection true
# Create dedicated break-glass admin account
gam create user breakglass-admin@corp.com \
firstname "Break" lastname "Glass Admin" \
password "$(openssl rand -base64 32)" \
changepassword true \
org "/Emergency Accounts"
# Assign super admin role to break-glass account
gam create admin breakglass-admin@corp.com "Super Admin"
# Configure admin activity alerts
# Alert Center API - create alert for admin actions
cat > admin_alert_policy.json << 'EOF'
{
"alertPolicies": [
{
"name": "Super Admin Sign-In Alert",
"conditions": {
"eventType": "login",
"filterCriteria": "actor.adminRole=SUPER_ADMIN"
},
"notifications": {
"email": ["security-team@corp.com"],
"webhook": "https://siem.corp.com/webhook/google-admin"
}
},
{
"name": "Admin Role Change Alert",
"conditions": {
"eventType": "admin_role_change"
},
"notifications": {
"email": ["security-team@corp.com"]
}
}
]
}
EOFConfigure MFA policies that eliminate phishable authentication factors:
# Enforce 2-Step Verification for all organizational units
# Using Admin SDK Directory API
# Enable 2SV enforcement for the entire organization
gam update org "/" settings \
2sv_enforcement true \
2sv_enrollment_grace_period 14 \
2sv_new_user_enrollment_period 1
# Configure allowed 2SV methods - restrict to phishing-resistant only
# For high-security OUs: Security keys only
gam update org "/Executive" settings \
2sv_allowed_methods "SECURITY_KEY_ONLY"
# For general staff: Security keys or phone prompts (no SMS/voice)
gam update org "/" settings \
2sv_allowed_methods "SECURITY_KEY,PHONE_PROMPT" \
2sv_disallowed_methods "SMS,VOICE_CALL,BACKUP_CODES"
# Bulk check 2SV enrollment status
gam print users \
fields primaryEmail,isEnrolledIn2Sv,isEnforcedIn2Sv \
query "isEnrolledIn2Sv=false" > users_without_2sv.csv
# Count users without 2SV
echo "Users without 2SV enrolled:"
wc -l < users_without_2sv.csv
# Configure context-aware access policies
# Require 2SV + managed device for sensitive apps
cat > context_aware_policy.json << 'EOF'
{
"accessLevels": [
{
"name": "Managed Device Required",
"conditions": {
"devicePolicy": {
"requireScreenLock": true,
"requireAdminApproval": true,
"allowedEncryptionStatuses": ["ENCRYPTED"],
"requireCorpOwned": false
},
"requiredAccessLevels": ["VERIFIED_2SV"]
}
}
],
"applicationPolicies": [
{
"applications": ["Google Drive", "Gmail", "Admin Console"],
"accessLevel": "Managed Device Required"
}
]
}
EOFSet up SPF, DKIM, DMARC and advanced phishing protections:
# Step 3a: Configure SPF record
# Add to DNS TXT record for corp.com
echo 'DNS TXT Record for SPF:'
echo 'corp.com TXT "v=spf1 include:_spf.google.com ~all"'
echo ''
echo 'After testing, change ~all to -all (hard fail) for enforcement'
# Step 3b: Generate and configure DKIM signing
# Generate 2048-bit DKIM key via Admin Console or API
gam create dkim domain corp.com selector google bitlength 2048
echo 'Add DKIM DNS TXT record:'
echo 'google._domainkey.corp.com TXT "v=DKIM1; k=rsa; p=<public_key_from_admin_console>"'
# Verify DKIM is working
gam info dkim domain corp.com
# Step 3c: Configure DMARC policy
echo 'DNS TXT Record for DMARC (start with monitoring):'
echo '_dmarc.corp.com TXT "v=DMARC1; p=none; rua=mailto:dmarc-reports@corp.com; ruf=mailto:dmarc-forensics@corp.com; pct=100; adkim=s; aspf=s"'
echo ''
echo 'After 30 days monitoring, escalate to quarantine then reject:'
echo '_dmarc.corp.com TXT "v=DMARC1; p=reject; rua=mailto:dmarc-reports@corp.com; pct=100; adkim=s; aspf=s"'
# Step 3d: Enable advanced phishing and malware protection
# Configure in Admin Console > Security > Email Safety
gam update settings email_safety \
protect_against_domain_spoofing true \
protect_against_employee_spoofing true \
protect_against_inbound_spoofing true \
protect_unauthenticated_email true \
identify_spoofed_groups true \
auto_move_suspicious_to_spam true
# Configure attachment security
gam update settings email_safety \
protect_encrypted_attachments true \
protect_anomalous_attachment_types true \
protect_scripts_from_untrusted true \
whitelist_sender_domains "" \
apply_future_recommended_settings trueConfigure DLP rules to prevent sensitive data exfiltration:
# Create DLP rules for Gmail and Drive
# Using Google Workspace DLP API
cat > dlp_rules.json << 'EOF'
{
"dlpRules": [
{
"name": "PII Detection - SSN",
"description": "Detect Social Security Numbers in outbound email and Drive sharing",
"trigger": {
"contentMatchers": [
{
"infoType": "US_SOCIAL_SECURITY_NUMBER",
"likelihood": "LIKELY",
"minMatchCount": 1
}
],
"scope": ["GMAIL_OUTBOUND", "DRIVE_EXTERNAL_SHARE"]
},
"action": {
"blockAction": "QUARANTINE",
"notifyAdmin": true,
"notifyUser": true,
"userMessage": "This message contains a Social Security Number and has been quarantined for review.",
"auditLog": true
}
},
{
"name": "Credit Card Number Detection",
"description": "Block credit card numbers in outbound communications",
"trigger": {
"contentMatchers": [
{
"infoType": "CREDIT_CARD_NUMBER",
"likelihood": "LIKELY",
"minMatchCount": 1
}
],
"scope": ["GMAIL_OUTBOUND", "DRIVE_EXTERNAL_SHARE", "CHAT"]
},
"action": {
"blockAction": "BLOCK",
"notifyAdmin": true,
"notifyUser": true,
"auditLog": true
}
},
{
"name": "Confidential Document Detection",
"description": "Detect documents marked as Confidential or Internal Only",
"trigger": {
"contentMatchers": [
{
"customRegex": "(?i)(CONFIDENTIAL|INTERNAL ONLY|DO NOT DISTRIBUTE|RESTRICTED)",
"minMatchCount": 2
}
],
"metadataMatchers": [
{
"driveLabels": ["Confidential", "Restricted"]
}
],
"scope": ["DRIVE_EXTERNAL_SHARE"]
},
"action": {
"blockAction": "WARN",
"requireJustification": true,
"auditLog": true
}
}
]
}
EOF
echo "Apply DLP rules via Admin Console > Security > Data Protection"
echo "Or use the Google Workspace DLP API for programmatic deployment"Restrict which third-party applications can access organizational data:
# Configure OAuth app access control
# Admin Console > Security > API Controls > App Access Control
# Block all third-party apps by default, then allowlist approved ones
gam update org "/" settings \
third_party_app_access "BLOCKED" \
allow_users_to_install_apps false
# Allowlist approved applications
cat > approved_apps.json << 'EOF'
{
"allowedApps": [
{
"appId": "slack-app-id",
"name": "Slack",
"scopes": ["gmail.readonly", "calendar.readonly"],
"approvedBy": "security-team",
"reviewDate": "2026-01-15"
},
{
"appId": "zoom-app-id",
"name": "Zoom",
"scopes": ["calendar.events"],
"approvedBy": "security-team",
"reviewDate": "2026-01-15"
},
{
"appId": "salesforce-app-id",
"name": "Salesforce",
"scopes": ["gmail.send", "contacts.readonly"],
"approvedBy": "security-team",
"reviewDate": "2026-01-15"
}
]
}
EOF
# Audit current OAuth tokens granted by users
gam all users print tokens > oauth_tokens_audit.csv
echo "Review oauth_tokens_audit.csv for unauthorized third-party access"
# Revoke tokens for unapproved applications
gam all users deprovision tokens \
clientid "unapproved-app-client-id"
# Configure API scopes restriction
# Limit which API scopes third-party apps can request
gam update org "/" settings \
api_access_restricted true \
allowed_api_scopes "gmail.readonly,calendar.readonly,drive.readonly"Lock down data sharing controls:
# Configure Google Drive sharing restrictions
gam update org "/" settings \
drive_sharing_outside_domain "WHITELISTED_DOMAINS" \
drive_sharing_whitelisted_domains "partner1.com,partner2.com" \
drive_allow_file_requests false \
drive_shared_drive_creation "ADMIN_ONLY" \
drive_default_link_sharing "RESTRICTED"
# Configure sharing alerts
gam create alert \
name "External Sharing Alert" \
type "drive_external_share" \
condition "shared_outside_domain=true AND file_type IN ('spreadsheet','document','presentation')" \
action "notify_admin security-team@corp.com"
# Audit current external shares
gam all users print filelist \
fields id,name,owners,permissions \
query "visibility='anyoneWithLink' or visibility='anyoneCanFind'" \
> external_shares_audit.csv
echo "External shares requiring review:"
wc -l < external_shares_audit.csv
# Configure Google Groups security
gam update org "/" settings \
groups_external_members false \
groups_external_posting false \
groups_creation "ADMIN_ONLY" \
groups_allow_external_invitations false| Term | Definition |
|---|---|
| Advanced Protection Program (APP) | Google's strongest account security requiring FIDO2 security keys, blocking third-party app access, and enhanced identity verification for account recovery |
| Context-Aware Access | Security policy framework that evaluates device posture, location, and user identity before granting access to Google Workspace applications |
| DMARC | Domain-based Message Authentication, Reporting and Conformance protocol that prevents email domain spoofing by validating SPF and DKIM alignment |
| DLP Rule | Data Loss Prevention policy that scans content in Gmail, Drive, and Chat for sensitive data patterns and triggers block, quarantine, or warn actions |
| OAuth App Allowlisting | Admin control restricting which third-party applications can access organizational data through Google OAuth API scopes |
| 2-Step Verification (2SV) | Google's multi-factor authentication implementation supporting security keys, phone prompts, TOTP, and backup codes as second factors |
Context: Post-acquisition security audit reveals the acquired company's Google Workspace has no MFA enforcement, open external sharing, no DLP policies, and multiple unauthorized OAuth applications accessing user data.
Approach:
Pitfalls:
GOOGLE WORKSPACE SECURITY ASSESSMENT REPORT
=============================================
Tenant: corp.com
License: Enterprise Plus
Total Users: 3,847
Organizational Units: 12
AUTHENTICATION SECURITY
2SV Enforced: YES (all OUs)
2SV Enrollment: 3,712 / 3,847 (96.5%)
Security Keys Only: Executive OU (47 users)
Advanced Protection: 3 super admin accounts
Super Admin Count: 3 (within recommended limit)
EMAIL AUTHENTICATION
SPF: CONFIGURED (hard fail: -all)
DKIM: CONFIGURED (2048-bit, selector: google)
DMARC: ENFORCED (p=reject, 100%)
Anti-Phishing: ALL PROTECTIONS ENABLED
Anti-Spoofing: ENABLED (domain + employee name)
DATA PROTECTION
DLP Rules Active: 7
PII Detection: SSN, Credit Card, Passport
Content Labels: Confidential, Restricted
Custom Patterns: 3 organization-specific rules
DLP Violations (30d): 89 (67 blocked, 22 warned)
APPLICATION CONTROL
Third-Party App Policy: BLOCKED (allowlist mode)
Approved Apps: 12
Unauthorized Tokens: 0 (all revoked)
API Scope Restrictions: ENABLED
SHARING CONTROLS
External Sharing: RESTRICTED (allowlisted domains only)
Public Link Sharing: DISABLED
External Group Members: DISABLED
Shared Drive Creation: ADMIN ONLY© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (scripts, references) in skills/implementing-google-workspace-admin-security of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Implementing Google Workspace Admin Security next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Implementing Google Workspace Admin Security this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | |
| Google WorkspaceNousResearch/hermes-agent | 252k | 3 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Google WorkspaceTommy-yw/RunbookHermes | 546 | 2 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Community Google WorkspaceArgentAIOS/argentos-core | 126 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Google Workspacegoogle/adk-recipes | 10k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Gws Installjezweb/claude-skills | 1.1k | — | ~1.1k | Automated safety check: Pass | MIT |
NousResearch/hermes-agent
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python. An agent skill from NousResearch/hermes-agent.
Tommy-yw/RunbookHermes
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration for Hermes.
ArgentAIOS/argentos-core
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration for community skills.
google/adk-recipes
Read/write Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the gws CLI.
jezweb/claude-skills
Quick install of the Google Workspace CLI (gws) on an additional machine using existing OAuth credentials.
jezweb/claude-skills
Set up the Google Workspace CLI (gws) from scratch. An agent skill from jezweb/claude-skills.
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Works with
Categories
Hardens a Google Workspace tenant via Admin Console configuration: phishing-resistant MFA enforcement, DLP policies, email authentication (SPF/DKIM/DMARC), OAuth third-party app control, and…. Implementing Google Workspace Admin Security is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Hardens a Google Workspace tenant via Admin Console configuration: phishing-resistant MFA enforcement, DLP policies, email authentication (SPF/DKIM/DMARC), OAuth third-party app control, and external sharing restrictions.
Implementing Google Workspace Admin Security fits situations like: hardening a Google Workspace; enforcing MFA and OAuth app controls; configuring cloud office security administration.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a claude-code`. Or copy the skill folder (skills/implementing-google-workspace-admin-security in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/implementing-google-workspace-admin-security in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a codex`. Or copy the skill folder (skills/implementing-google-workspace-admin-security in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/implementing-google-workspace-admin-security in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-google-workspace-admin-security -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implementing-google-workspace-admin-security, .gemini/skills/implementing-google-workspace-admin-security, .github/skills/implementing-google-workspace-admin-security and .opencode/skills/implementing-google-workspace-admin-security in your project.
Going by SKILL.md and its folder, Implementing Google Workspace Admin Security needs Python for the scripts in its folder, the command-line tools its instructions call (openssl) and credentials named SECURITY_KEY. Our summary lists: Python 3; A credential in SECURITY_KEY.
SKILL.md names 1 domain. In commands or code: siem.corp.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Implementing Google Workspace Admin Security is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 558 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Implementing Google Workspace Admin Security: Google Workspace (NousResearch/hermes-agent, 252k stars), Google Workspace (Tommy-yw/RunbookHermes, 546 stars), Community Google Workspace (ArgentAIOS/argentos-core, 126 stars) and Google Workspace (google/adk-recipes, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,922 GitHub stars. The repository holds 637 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.