Agent skill

Implementing Browser Isolation For Zero Trust

by mukul975 in mukul975/Anthropic-Cybersecurity-Skills

Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture.

Apache-2.0Auto-check passedSecurity

Install Implementing Browser Isolation For Zero Trust

skills CLI
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-browser-isolation-for-zero-trust -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-browser-isolation-for-zero-trust --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/implementing-browser-isolation-for-zero-trust .claude/skills/implementing-browser-isolation-for-zero-trust && rm -rf skills-src

Use ~/.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/

Facts

Skill name
implementing-browser-isolation-for-zero-trust
GitHub stars
34k
Token cost
~3.5k tokens
SKILL.md length
300 words
Files
4 (incl. scripts, references)
Skills in repo
639
Repo updated
First seen
Licence
Apache-2.0

At a glance

Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture.

  • Works in 5 steps: URL Categorization and Risk Classification → Isolation Policy Configuration → Content Disarming and Reconstruction (CDR) → …
  • Hardening web access against zero-day exploits
  • SKILL.md covers When to Use, Prerequisites, Instructions and Examples
  • Runs Python scripts from its folder; reaches docs.google.com and unknown-sketchy-domain.xyz

What it does

Implementing Browser Isolation For Zero Trust is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture. Implements isolation policies with URL categorization and risk-based routing, content disarming and reconstruction (CDR) for file sanitization, data loss prevention controls within isolated sessions, and integration with Secure Web Gateway and ZTNA platforms. Based on Cloudflare Browser Isolation, Menlo Security, and Zscaler RBI approaches. Use when hardening web access against zero-day exploits, phishing, credential theft…

Its SKILL.md is about 3.5k 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 Security. It works with Cloudflare. 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.

When your agent uses it

  • Hardening web access against zero-day exploits
  • Credential theft
  • Browser-based data exfiltration

Example prompts

  • “Use the implementing-browser-isolation-for-zero-trust skill to deploy remote browser isolation (RBI) as a core component of a Zero Trust architecture”
  • “/implementing-browser-isolation-for-zero-trust”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. URL Categorization and Risk Classification
  2. Isolation Policy Configuration
  3. Content Disarming and Reconstruction (CDR)
  4. Session Control and Monitoring
  5. Integration with Zero Trust Platform

What it can do on your machine

Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • docs.google.com
    • unknown-sketchy-domain.xyz
    • pac.acme.com
    • sensitive-app.acme.com
    • micr0soft-login.phishing.com
    • mail.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Implementing Browser Isolation For Zero Trust loads about 3.5k tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 150 tokens; SKILL.md has 300 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~150
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.8k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 300 words, ~3,485 tokens.

Download SKILL.mdSave it as .claude/skills/implementing-browser-isolation-for-zero-trust/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
implementing-browser-isolation-for-zero-trust
description
Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture. Implements isolation policies with URL categorization and risk-based routing, content disarming and reconstruction (CDR) for file sanitization, data loss prevention controls within isolated sessions, and integration with Secure Web Gateway and ZTNA platforms. Based on Cloudflare Browser Isolation, Menlo Security, and Zscaler RBI approaches. Use when hardening web access against zero-day exploits, phishing, credential theft, and browser-based data exfiltration.
domain
cybersecurity
subdomain
network-security
tags
browser-isolation, zero-trust, RBI, CDR, URL-categorization, content-disarming, secure-web-gateway
version
1.0
author
mukul975
license
Apache-2.0
nist_csf
PR.IR-01, DE.CM-01, ID.AM-03, PR.DS-02
mitre_attack
T1046, T1040, T1557, T1071, T1003
mitre_f3.version
1.1
mitre_f3.tactics
initial-access, positioning, execution

Implementing Browser Isolation for Zero Trust

When to Use

  • When deploying remote browser isolation as part of a Zero Trust security architecture
  • When protecting users from zero-day browser exploits and drive-by downloads
  • When implementing content disarming and reconstruction for file downloads
  • When enforcing data loss prevention policies for web browsing sessions
  • When securing access to untrusted or uncategorized websites
  • When integrating browser isolation with existing SWG and ZTNA infrastructure
  • When protecting against phishing and credential theft via isolated rendering

Prerequisites

  • Familiarity with Zero Trust architecture principles and network security
  • Understanding of Secure Web Gateway (SWG) and proxy deployment models
  • Access to a test or lab environment for policy validation
  • Python 3.8+ with required dependencies installed
  • DNS and proxy infrastructure for traffic routing

Instructions

Phase 1: URL Categorization and Risk Classification

Build a URL categorization engine that classifies websites by risk level to determine isolation policy. URLs are scored based on threat intelligence feeds, domain reputation, content category, and historical risk indicators.

python
from agent import BrowserIsolationPolicyEngine

engine = BrowserIsolationPolicyEngine(
    organization="Acme Corp",
    default_isolation_mode="isolate_risky",
)

# Classify a URL and determine isolation action
result = engine.classify_url("https://docs.google.com/spreadsheets/d/abc123")
print(f"Category: {result['category']}")
print(f"Risk Level: {result['risk_level']}")
print(f"Isolation Action: {result['action']}")
# Output: Category: cloud_productivity
#         Risk Level: low
#         Action: allow_direct

result = engine.classify_url("https://unknown-sketchy-domain.xyz/download.html")
print(f"Category: {result['category']}")
print(f"Risk Level: {result['risk_level']}")
print(f"Isolation Action: {result['action']}")
# Output: Category: uncategorized
#         Risk Level: high
#         Action: full_isolation
Phase 2: Isolation Policy Configuration

Define isolation policies that map URL categories and risk levels to specific isolation modes and DLP restrictions. Policies support granular controls including clipboard, file download, upload, and printing restrictions.

python
# Configure isolation policies
engine.add_isolation_policy(
    name="Block Uncategorized Sites",
    description="Fully isolate all uncategorized or newly registered domains",
    match_criteria={
        "url_categories": ["uncategorized", "newly_registered"],
        "risk_levels": ["high", "critical"],
    },
    isolation_mode="full_isolation",
    dlp_controls={
        "disable_copy_paste": True,
        "disable_download": True,
        "disable_upload": True,
        "disable_printing": True,
        "disable_keyboard_input": False,
        "watermark_session": True,
    },
)

engine.add_isolation_policy(
    name="Isolate Webmail with DLP",
    description="Isolate personal webmail with download restrictions",
    match_criteria={
        "url_categories": ["webmail"],
        "domains": ["mail.google.com", "outlook.live.com", "mail.yahoo.com"],
    },
    isolation_mode="read_only_isolation",
    dlp_controls={
        "disable_copy_paste": True,
        "disable_download": True,
        "disable_upload": True,
        "disable_printing": True,
        "disable_keyboard_input": False,
        "watermark_session": False,
    },
)

engine.add_isolation_policy(
    name="CDR for File Downloads",
    description="Apply content disarm and reconstruction to all file downloads",
    match_criteria={
        "url_categories": ["*"],
        "file_types": ["pdf", "docx", "xlsx", "pptx", "zip", "exe", "msi"],
    },
    isolation_mode="cdr_passthrough",
    cdr_config={
        "strip_macros": True,
        "strip_embedded_objects": True,
        "strip_javascript": True,
        "strip_active_content": True,
        "flatten_pdf": True,
        "reconstruct_to_safe_format": True,
        "max_file_size_mb": 50,
        "allowed_file_types": ["pdf", "docx", "xlsx", "pptx", "png", "jpg"],
    },
)

engine.add_isolation_policy(
    name="Allow Trusted SaaS Direct",
    description="Allow direct access to sanctioned SaaS applications",
    match_criteria={
        "url_categories": ["cloud_productivity", "business_saas"],
        "domains": [
            "*.office365.com", "*.office.com", "*.microsoft.com",
            "*.salesforce.com", "*.slack.com", "*.github.com",
        ],
        "risk_levels": ["low"],
    },
    isolation_mode="allow_direct",
    dlp_controls={
        "disable_copy_paste": False,
        "disable_download": False,
        "disable_upload": False,
        "log_all_downloads": True,
    },
)

# List all policies
for policy in engine.list_policies():
    print(f"  [{policy['priority']}] {policy['name']} -> {policy['isolation_mode']}")
Phase 3: Content Disarming and Reconstruction (CDR)

Implement CDR processing to sanitize downloaded files by deconstructing them, stripping potentially malicious elements (macros, embedded objects, scripts), and reconstructing clean versions that preserve usability.

python
# Process a file through CDR
cdr_result = engine.process_file_cdr(
    file_path="/tmp/downloads/quarterly_report.docx",
    source_url="https://partner-portal.example.com/reports/q4.docx",
    cdr_profile="strict",
)

print(f"Original file: {cdr_result['original']['filename']}")
print(f"Original size: {cdr_result['original']['size_bytes']} bytes")
print(f"Threats found: {cdr_result['threats_found']}")
for threat in cdr_result['threats_detail']:
    print(f"  - {threat['type']}: {threat['description']} [{threat['action']}]")
print(f"Clean file: {cdr_result['reconstructed']['filename']}")
print(f"Clean size: {cdr_result['reconstructed']['size_bytes']} bytes")
print(f"File integrity preserved: {cdr_result['reconstructed']['usable']}")

# Example output:
# Original file: quarterly_report.docx
# Original size: 245760 bytes
# Threats found: 3
#   - macro: VBA macro with AutoOpen trigger [STRIPPED]
#   - embedded_ole: Embedded OLE object (executable) [STRIPPED]
#   - external_link: External template reference [STRIPPED]
# Clean file: quarterly_report_clean.docx
# Clean size: 198432 bytes
# File integrity preserved: True
Phase 4: Session Control and Monitoring

Implement real-time session monitoring for isolated browsing sessions with keystroke logging policy, clipboard interception, and download tracking. Integrate with SIEM for security event correlation.

python
# Create an isolation session
session = engine.create_isolation_session(
    user_id="jsmith@acme.com",
    user_groups=["engineering", "contractors"],
    device_posture={
        "os": "Windows 11",
        "managed": True,
        "edr_running": True,
        "disk_encrypted": True,
        "os_patched": True,
    },
    target_url="https://external-vendor.example.com/portal",
)

print(f"Session ID: {session['session_id']}")
print(f"Isolation Mode: {session['isolation_mode']}")
print(f"Applied Policy: {session['applied_policy']}")
print(f"DLP Controls: {json.dumps(session['dlp_controls'], indent=2)}")

# Monitor session events
events = engine.get_session_events(session_id=session["session_id"])
for event in events:
    print(f"  [{event['timestamp']}] {event['event_type']}: {event['details']}")

# Generate session audit report
audit = engine.generate_session_audit(
    user_id="jsmith@acme.com",
    date_range=("2026-03-01", "2026-03-19"),
)
print(f"Total sessions: {audit['total_sessions']}")
print(f"Isolated sessions: {audit['isolated_sessions']}")
print(f"Files processed via CDR: {audit['cdr_processed_files']}")
print(f"DLP violations: {audit['dlp_violations']}")
Phase 5: Integration with Zero Trust Platform

Integrate browser isolation with the broader Zero Trust architecture including identity provider, device posture checks, and conditional access policies.

python
# Define Zero Trust conditional access integration
zt_policy = engine.create_zero_trust_integration(
    identity_provider="Azure AD",
    conditional_access_rules=[
        {
            "name": "Unmanaged Device Isolation",
            "condition": {"device_managed": False},
            "action": "full_isolation",
            "dlp_override": {"disable_download": True, "disable_upload": True},
        },
        {
            "name": "High Risk User Isolation",
            "condition": {"user_risk_level": "high"},
            "action": "full_isolation",
            "dlp_override": {"disable_copy_paste": True, "watermark_session": True},
        },
        {
            "name": "Contractor Restricted Access",
            "condition": {"user_group": "contractors"},
            "action": "read_only_isolation",
            "dlp_override": {"disable_download": True, "disable_printing": True},
        },
        {
            "name": "Privileged Admin Isolation",
            "condition": {"user_group": "admins", "target_category": "admin_console"},
            "action": "full_isolation",
            "dlp_override": {"watermark_session": True, "record_session": True},
        },
    ],
    swg_integration={
        "proxy_mode": "explicit",
        "pac_url": "https://pac.acme.com/proxy.pac",
        "ssl_inspection": True,
        "bypass_domains": ["*.acme.internal"],
    },
)

# Evaluate a request against all policies
decision = engine.evaluate_access_request(
    user_id="contractor@vendor.com",
    user_groups=["contractors"],
    device_posture={"managed": False, "edr_running": False},
    target_url="https://sensitive-app.acme.com/dashboard",
    user_risk_level="medium",
)
print(f"Decision: {decision['action']}")
print(f"Matched Rules: {[r['name'] for r in decision['matched_rules']]}")
print(f"DLP Controls: {decision['effective_dlp_controls']}")

Examples

Quick Policy Deployment for Phishing Protection
python
engine = BrowserIsolationPolicyEngine(default_isolation_mode="isolate_risky")

# Isolate all links from email
engine.add_isolation_policy(
    name="Email Link Isolation",
    description="Isolate all URLs clicked from email clients",
    match_criteria={
        "referrer_categories": ["email_client"],
        "url_categories": ["*"],
    },
    isolation_mode="full_isolation",
    dlp_controls={
        "disable_keyboard_input": True,
        "disable_download": True,
        "watermark_session": True,
    },
)

# Test against a phishing URL
result = engine.evaluate_access_request(
    user_id="user@acme.com",
    target_url="https://micr0soft-login.phishing.com/auth",
    referrer="https://mail.google.com",
    user_risk_level="low",
)
print(f"Action: {result['action']}")  # full_isolation
CDR Pipeline for All Downloads
python
engine = BrowserIsolationPolicyEngine()

# Scan a batch of downloaded files through CDR
files = [
    "/tmp/downloads/invoice.pdf",
    "/tmp/downloads/contract.docx",
    "/tmp/downloads/data_export.xlsx",
    "/tmp/downloads/presentation.pptx",
]

batch_result = engine.batch_cdr_process(
    files=files,
    cdr_profile="strict",
    quarantine_on_threat=True,
)

print(f"Processed: {batch_result['total_processed']}")
print(f"Clean: {batch_result['clean_count']}")
print(f"Threats neutralized: {batch_result['threats_neutralized']}")
print(f"Quarantined: {batch_result['quarantined_count']}")
for f in batch_result["results"]:
    status = "CLEAN" if f["clean"] else "SANITIZED"
    print(f"  [{status}] {f['filename']}: {f['threats_found']} threats")
Generating Isolation Policy Compliance Report
python
engine = BrowserIsolationPolicyEngine()

report = engine.generate_compliance_report(
    date_range=("2026-03-01", "2026-03-19"),
    include_metrics=True,
)

print(f"Total web requests: {report['total_requests']}")
print(f"Isolated requests: {report['isolated_requests']} ({report['isolation_rate']}%)")
print(f"CDR processed files: {report['cdr_stats']['total_files']}")
print(f"Threats neutralized: {report['cdr_stats']['threats_neutralized']}")
print(f"DLP violations blocked: {report['dlp_violations_blocked']}")
print(f"Zero-day attacks prevented: {report['zero_day_blocked']}")

© 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

Files

SKILL.md and 3 other files (scripts, references) in skills/implementing-browser-isolation-for-zero-trust of mukul975/Anthropic-Cybersecurity-Skills.

  • SKILL.md
  • LICENSE
  • references/api-reference.md
  • scripts/agent.py

Open the folder on GitHubat commit 54a7988

Compare with similar skills

Implementing Browser Isolation For Zero Trust 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.

Implementing Browser Isolation For Zero Trust compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implementing Browser Isolation For Zero Trust this skillmukul975/Anthropic-Cybersecurity-Skills34k—~3.5kAutomated safety check: PassApache-2.0
Cloudflare Security Auditsickn33/agentic-awesome-skills47k1 repos~3.3kAutomated safety check: PassMIT
External Enumerationforefy/.context152—~3.1kAutomated safety check: PassMIT
Origin Ip Discoveryuphiago/recon-skills1.3k—~1.7kAutomated safety check: PassMIT
Webhome Extension Builderwebhtv/webhtv1.7k—~2.8kAutomated safety check: PassGPL-3.0
Audit Gitbook IntegrationGitbookIO/integrations131—~1.2kAutomated safety check: PassNone

Similar skills

  • Cloudflare Security Audit

    sickn33/agentic-awesome-skills

    Audit authorized codebases for exploitable vulnerabilities using scoped reconnaissance, adversarial review, validation, and structured reporting.

    47k GitHub starsUsed in 1 repo~3.3k tokens
    SecurityAuto-check passed
  • External Enumeration

    forefy/.context

    Passively map a company's domains, subdomains, DNS ownership, tech stack, and CDNs.

    152 GitHub stars~3.1k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Origin Ip Discovery

    uphiago/recon-skills

    Discover origin IPs behind CDN/WAF via favicon hash, DNS history, and SSL certs.

    1.3k GitHub stars~1.7k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Build, review, debug, reverse-engineer, and package WebHome injected extension scripts for FongMi/WebHome App WebView pages.

    1.7k GitHub stars~2.8k tokensUpdated today
    SecurityAuto-check passed
  • Audit Gitbook Integration

    GitbookIO/integrations

    Audit GitBook integrations for script injection, sensitive-data access, unsafe requests, authorization gaps, and manifest or dependency risk.

    131 GitHub stars~1.2k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Blueprint Cloudflare Security

    receptron/mulmoterminal

    Review the finished Worker against OWASP Top 10:2025, fix what is exploitable, prove each fix with a test, and report.

    236 GitHub stars~1.2k tokensUpdated today
    SecurityAuto-check: notes

More from mukul975/Anthropic-Cybersecurity-Skills

All 639 skills in this repo
  • Campaign Attribution Evidence Analysis

    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.

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Go Malware Analysis in Ghidra

    mukul975/Anthropic-Cybersecurity-Skills

    Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • LNK and Jump List Forensics

    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.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Malware Persistence Analysis with Autoruns

    mukul975/Anthropic-Cybersecurity-Skills

    Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.

    34k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • NTFS MFT Deleted File Recovery

    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.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Network Covert Channel Analysis

    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.

    34k GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Implementing Browser Isolation For Zero Trust

What does Implementing Browser Isolation For Zero Trust do?

Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture. Implementing Browser Isolation For Zero Trust is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture.

When should I use Implementing Browser Isolation For Zero Trust?

Implementing Browser Isolation For Zero Trust fits situations like: hardening web access against zero-day exploits; credential theft; browser-based data exfiltration.

How do I install Implementing Browser Isolation For Zero Trust in Claude Code?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-browser-isolation-for-zero-trust -a claude-code`. Or copy the skill folder (skills/implementing-browser-isolation-for-zero-trust in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/implementing-browser-isolation-for-zero-trust in your project. Claude Code loads it when a task matches its description.

How do I install Implementing Browser Isolation For Zero Trust in Codex?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-browser-isolation-for-zero-trust -a codex`. Or copy the skill folder (skills/implementing-browser-isolation-for-zero-trust in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/implementing-browser-isolation-for-zero-trust in your project. Codex loads it when a task matches its description.

Can I use Implementing Browser Isolation For Zero Trust in Cursor, Gemini CLI or GitHub Copilot?

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-browser-isolation-for-zero-trust -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-browser-isolation-for-zero-trust, .gemini/skills/implementing-browser-isolation-for-zero-trust, .github/skills/implementing-browser-isolation-for-zero-trust and .opencode/skills/implementing-browser-isolation-for-zero-trust in your project.

What does Implementing Browser Isolation For Zero Trust need to run?

Going by SKILL.md and its folder, Implementing Browser Isolation For Zero Trust needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Implementing Browser Isolation For Zero Trust access the network?

SKILL.md names 6 domains. In commands or code: docs.google.com, unknown-sketchy-domain.xyz, pac.acme.com, sensitive-app.acme.com, micr0soft-login.phishing.com and mail.google.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Implementing Browser Isolation For Zero Trust safe to install?

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.

What licence does Implementing Browser Isolation For Zero Trust use?

Implementing Browser Isolation For Zero Trust 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.

How many tokens does Implementing Browser Isolation For Zero Trust use?

About 3.5k tokens (SKILL.md is roughly 14k 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 2.3k tokens, read only when the agent opens those files.

What are the alternatives to Implementing Browser Isolation For Zero Trust?

Skills that share tags, products or a category with Implementing Browser Isolation For Zero Trust: Cloudflare Security Audit (sickn33/agentic-awesome-skills, 47k stars), External Enumeration (forefy/.context, 152 stars), Origin Ip Discovery (uphiago/recon-skills, 1.3k stars) and Webhome Extension Builder (webhtv/webhtv, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implementing Browser Isolation For Zero Trust?

mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 33,870 GitHub stars. The repository holds 639 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.