Cloudflare Security Audit
sickn33/agentic-awesome-skills
Audit authorized codebases for exploitable vulnerabilities using scoped reconnaissance, adversarial review, validation, and structured reporting.
Agent skill
Deploys remote browser isolation (RBI) as a core component of a Zero Trust architecture.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-browser-isolation-for-zero-trust -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-browser-isolation-for-zero-trust --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-browser-isolation-for-zero-trust .claude/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .claude/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trustType 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-browser-isolation-for-zero-trust -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-browser-isolation-for-zero-trust --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-browser-isolation-for-zero-trust .agents/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .agents/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trust -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-browser-isolation-for-zero-trust --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-browser-isolation-for-zero-trust .cursor/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .cursor/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trust--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-browser-isolation-for-zero-trust -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-browser-isolation-for-zero-trust --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-browser-isolation-for-zero-trust .gemini/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .gemini/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trustInstalls 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-browser-isolation-for-zero-trust -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-browser-isolation-for-zero-trust .github/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .github/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trust -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-browser-isolation-for-zero-trust --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-browser-isolation-for-zero-trust .opencode/skills/implementing-browser-isolation-for-zero-trust && 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-browser-isolation-for-zero-trust" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-browser-isolation-for-zero-trust into .opencode/skills/implementing-browser-isolation-for-zero-trust/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-browser-isolation-for-zero-trust", 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-browser-isolation-for-zero-trustDeploys 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. 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.
5 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.
From 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:
docs.google.comunknown-sketchy-domain.xyzpac.acme.comsensitive-app.acme.commicr0soft-login.phishing.commail.google.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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). 300 words, ~3,485 tokens.
.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.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.
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_isolationDefine 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.
# 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']}")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.
# 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: TrueImplement real-time session monitoring for isolated browsing sessions with keystroke logging policy, clipboard interception, and download tracking. Integrate with SIEM for security event correlation.
# 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']}")Integrate browser isolation with the broader Zero Trust architecture including identity provider, device posture checks, and conditional access policies.
# 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']}")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_isolationengine = 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")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
SKILL.md and 3 other files (scripts, references) in skills/implementing-browser-isolation-for-zero-trust of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Implementing Browser Isolation For Zero Trust this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Cloudflare Security Auditsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| External Enumerationforefy/.context | 152 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Origin Ip Discoveryuphiago/recon-skills | 1.3k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Webhome Extension Builderwebhtv/webhtv | 1.7k | — | ~2.8k | Automated safety check: Pass | GPL-3.0 | |
| Audit Gitbook IntegrationGitbookIO/integrations | 131 | — | ~1.2k | Automated safety check: Pass | None |
sickn33/agentic-awesome-skills
Audit authorized codebases for exploitable vulnerabilities using scoped reconnaissance, adversarial review, validation, and structured reporting.
forefy/.context
Passively map a company's domains, subdomains, DNS ownership, tech stack, and CDNs.
uphiago/recon-skills
Discover origin IPs behind CDN/WAF via favicon hash, DNS history, and SSL certs.
webhtv/webhtv
Build, review, debug, reverse-engineer, and package WebHome injected extension scripts for FongMi/WebHome App WebView pages.
GitbookIO/integrations
Audit GitBook integrations for script injection, sensitive-data access, unsafe requests, authorization gaps, and manifest or dependency risk.
receptron/mulmoterminal
Review the finished Worker against OWASP Top 10:2025, fix what is exploitable, prove each fix with a test, and report.
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
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.
Implementing Browser Isolation For Zero Trust fits situations like: hardening web access against zero-day exploits; credential theft; browser-based data exfiltration.
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.
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.
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.
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.
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.
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 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.
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.
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.
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.