Policy Opa
AgentSecOps/SecOpsAgentKit
Policy-as-code enforcement and compliance validation using Open Policy Agent (OPA).
Agent skill
Implements 802.1X port-based network access control using RADIUS authentication, PacketFence NAC, and switch configuration to enforce identity-based access policies, posture assessment, and…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-network-access-control -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-network-access-control --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-network-access-control .claude/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .claude/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-controlType 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-network-access-control -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-network-access-control --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-network-access-control .agents/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .agents/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-control -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-network-access-control --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-network-access-control .cursor/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .cursor/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-control--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-network-access-control -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills implementing-network-access-control --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-network-access-control .gemini/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .gemini/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-controlInstalls 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-network-access-control -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-network-access-control .github/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .github/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-control -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-network-access-control --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-network-access-control .opencode/skills/implementing-network-access-control && 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-network-access-control" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/implementing-network-access-control into .opencode/skills/implementing-network-access-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementing-network-access-control", 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-network-access-controlImplements 802.1X port-based network access control using RADIUS authentication, PacketFence NAC, and switch configuration to enforce identity-based access policies, posture assessment, and…
Implementing Network Access Control is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Implements 802.1X port-based network access control using RADIUS authentication, PacketFence NAC, and switch configuration to enforce identity-based access policies, posture assessment, and automatic VLAN assignment for authorized devices. Use when enforcing zero-trust access at the network edge, quarantining non-compliant endpoints, meeting PCI-DSS/HIPAA/SOC 2 access requirements, or onboarding BYOD devices with automated provisioning.
Its SKILL.md is about 3.8k 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 Legal & Compliance, covering Authorization and RBAC, Healthcare and finance regulation and SOC 2 and security compliance. 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:
aptcurlFrom 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:
inverse.caFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GPG_PUBLIC_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Implementing Network Access Control loads about 3.8k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 602 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 noted patterns worth knowing about, such as sudo or a known installer.
sudo apt install -y freeradius freeradius-utils freeradius-ldapsudo tee /etc/freeradius/3.0/clients.conf << 'EOF'sudo tee /etc/freeradius/3.0/mods-available/ldap << 'EOF'sudo ln -s /etc/freeradius/3.0/mods-available/ldap /etc/freeradius/3.0/mods-enabled/ldapsudo tee /etc/freeradius/3.0/policy.d/vlan-assignment << 'EOF'sudo tee /etc/freeradius/3.0/mods-available/eap << 'EAPEOF'sudo freeradius -X://inverse.ca/downloads/GPG_PUBLIC_KEY | sudo gpg --dearmor -o /etc/apt/keyrings/inverse.gpgsudo tee /etc/apt/sources.list.d/packetfence.listsudo apt update && sudo apt install -y packetfenceAutomated 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). 602 words, ~3,770 tokens.
.claude/skills/implementing-network-access-control/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Do not use as a standalone security solution without complementary controls, for networks with devices that do not support 802.1X supplicants, or without proper fallback mechanisms for critical infrastructure.
# Install FreeRADIUS
sudo apt install -y freeradius freeradius-utils freeradius-ldap
# Configure RADIUS clients (switches that authenticate against RADIUS)
sudo tee /etc/freeradius/3.0/clients.conf << 'EOF'
client switch-core-01 {
ipaddr = 10.10.100.1
secret = R4d1u5_S3cr3t_K3y!
shortname = core-switch
nastype = cisco
}
client switch-access-01 {
ipaddr = 10.10.100.10
secret = R4d1u5_S3cr3t_K3y!
shortname = access-switch-01
nastype = cisco
}
client switch-access-02 {
ipaddr = 10.10.100.11
secret = R4d1u5_S3cr3t_K3y!
shortname = access-switch-02
nastype = cisco
}
EOF
# Configure LDAP module for Active Directory integration
sudo tee /etc/freeradius/3.0/mods-available/ldap << 'EOF'
ldap {
server = 'ldap://dc01.corp.example.com'
identity = 'CN=radius-svc,OU=Service Accounts,DC=corp,DC=example,DC=com'
password = 'ServiceAccountPassword123!'
base_dn = 'DC=corp,DC=example,DC=com'
user {
base_dn = "${..base_dn}"
filter = "(sAMAccountName=%{%{Stripped-User-Name}:-%{User-Name}})"
}
group {
base_dn = "${..base_dn}"
filter = "(objectClass=group)"
membership_attribute = 'memberOf'
}
}
EOF
sudo ln -s /etc/freeradius/3.0/mods-available/ldap /etc/freeradius/3.0/mods-enabled/ldap# Configure authorization policies for dynamic VLAN assignment
sudo tee /etc/freeradius/3.0/policy.d/vlan-assignment << 'EOF'
# VLAN assignment based on group membership
vlan_assignment {
if (&LDAP-Group[*] == "CN=IT-Staff,OU=Groups,DC=corp,DC=example,DC=com") {
update reply {
Tunnel-Type = VLAN
Tunnel-Medium-Type = IEEE-802
Tunnel-Private-Group-ID = "10"
}
}
elsif (&LDAP-Group[*] == "CN=Developers,OU=Groups,DC=corp,DC=example,DC=com") {
update reply {
Tunnel-Type = VLAN
Tunnel-Medium-Type = IEEE-802
Tunnel-Private-Group-ID = "15"
}
}
elsif (&LDAP-Group[*] == "CN=Finance,OU=Groups,DC=corp,DC=example,DC=com") {
update reply {
Tunnel-Type = VLAN
Tunnel-Medium-Type = IEEE-802
Tunnel-Private-Group-ID = "20"
}
}
else {
# Default: Guest VLAN for unknown users
update reply {
Tunnel-Type = VLAN
Tunnel-Medium-Type = IEEE-802
Tunnel-Private-Group-ID = "40"
}
}
}
EOF
# Add vlan_assignment to the authorize section
# Edit /etc/freeradius/3.0/sites-enabled/default
# In the authorize section, add: vlan_assignment
# Configure EAP for 802.1X authentication
sudo tee /etc/freeradius/3.0/mods-available/eap << 'EAPEOF'
eap {
default_eap_type = peap
timer_expire = 60
max_sessions = 4096
tls-config tls-common {
private_key_file = /etc/freeradius/3.0/certs/server.key
certificate_file = /etc/freeradius/3.0/certs/server.pem
ca_file = /etc/freeradius/3.0/certs/ca.pem
dh_file = /etc/freeradius/3.0/certs/dh
cipher_list = "HIGH:!aNULL:!MD5"
tls_min_version = "1.2"
}
peap {
tls = tls-common
default_eap_type = mschapv2
virtual_server = inner-tunnel
}
tls {
tls = tls-common
}
}
EAPEOF
# Start FreeRADIUS in debug mode for testing
sudo freeradius -X
# Test authentication
radtest testuser TestPassword123 localhost 0 testing123! Enable AAA on the switch
enable
configure terminal
aaa new-model
aaa authentication dot1x default group radius
aaa authorization network default group radius
aaa accounting dot1x default start-stop group radius
! Configure RADIUS server
radius server FREERADIUS
address ipv4 10.10.100.200 auth-port 1812 acct-port 1813
key R4d1u5_S3cr3t_K3y!
exit
! Enable 802.1X globally
dot1x system-auth-control
! Configure access ports for 802.1X
interface range GigabitEthernet1/0/1-24
switchport mode access
switchport access vlan 999
authentication port-control auto
authentication order dot1x mab
authentication priority dot1x mab
dot1x pae authenticator
dot1x timeout tx-period 10
mab
authentication event fail action authorize vlan 999
authentication event no-response action authorize vlan 40
authentication host-mode multi-auth
spanning-tree portfast
exit
! Configure MAB (MAC Authentication Bypass) for devices without 802.1X
! Devices like printers, IP phones that cannot run a supplicant
interface range GigabitEthernet1/0/25-36
switchport mode access
switchport access vlan 999
authentication port-control auto
authentication order mab
mab
authentication event fail action authorize vlan 999
authentication host-mode single-host
spanning-tree portfast
exit
! Configure guest VLAN for unauthenticated devices
interface range GigabitEthernet1/0/1-24
authentication event no-response action authorize vlan 40
authentication event fail action authorize vlan 999
exit
! Configure critical VLAN for RADIUS server unavailability
interface range GigabitEthernet1/0/1-36
authentication event server dead action authorize vlan 10
authentication event server alive action reinitialize
exit# Install PacketFence
curl -fsSL https://inverse.ca/downloads/GPG_PUBLIC_KEY | sudo gpg --dearmor -o /etc/apt/keyrings/inverse.gpg
echo "deb [signed-by=/etc/apt/keyrings/inverse.gpg] https://inverse.ca/downloads/PacketFence/debian bookworm bookworm" | \
sudo tee /etc/apt/sources.list.d/packetfence.list
sudo apt update && sudo apt install -y packetfence
# Run the PacketFence configurator
sudo /usr/local/pf/bin/pfcmd configreload
# Access web admin: https://<packetfence-ip>:1443
# Configure PacketFence connection profiles
# Admin UI: Configuration > Policies and Access Control > Connection Profiles
# Create compliance check (Windows Update status)
# Admin UI: Configuration > Compliance > Scan Engines
# Add: Windows Update compliance check
# Remediation VLAN: 999 (quarantine)
# Configure RADIUS integration
# PacketFence acts as a RADIUS proxy, receiving requests from switches
# and enforcing posture-based VLAN assignment
# Edit /usr/local/pf/conf/switches.conf
sudo tee -a /usr/local/pf/conf/switches.conf << 'EOF'
[10.10.100.10]
description=Access Switch 01
type=Cisco::Catalyst_2960
mode=production
radiusSecret=R4d1u5_S3cr3t_K3y!
SNMPVersion=2c
SNMPCommunityRead=public
SNMPCommunityWrite=private
VlanMap=Y
registrationVlan=40
isolationVlan=999
normalVlan=10
EOF# Windows Group Policy for 802.1X configuration
# Computer Configuration > Policies > Windows Settings > Security Settings
# > System Services > Wired AutoConfig: Automatic
# > Network Policies:
# Authentication method: Microsoft: Protected EAP (PEAP)
# Inner method: EAP-MSCHAPv2
# Trusted Root CA: Corporate CA
# Linux 802.1X configuration with wpa_supplicant
sudo tee /etc/wpa_supplicant/wpa_supplicant-wired.conf << 'EOF'
ctrl_interface=/var/run/wpa_supplicant
ap_scan=0
network={
key_mgmt=IEEE8021X
eap=PEAP
identity="testuser@corp.example.com"
password="UserPassword123"
ca_cert="/etc/ssl/certs/corporate-ca.pem"
phase2="auth=MSCHAPV2"
}
EOF
# Start wpa_supplicant for wired 802.1X
sudo wpa_supplicant -i eth0 -D wired -c /etc/wpa_supplicant/wpa_supplicant-wired.conf -B
# Verify authentication status
wpa_cli -i eth0 status
# macOS: System Preferences > Network > Ethernet > 802.1X
# Configure with PEAP and corporate credentials# Test 1: Authenticated device gets correct VLAN
# Connect a corporate laptop with 802.1X configured
# Verify VLAN assignment on the switch:
# show authentication sessions interface Gi1/0/1
# Expected:
# Session ID: 0A0A0A01000000010001
# Status: Authorized
# Domain: DATA
# Oper host mode: multi-auth
# Oper control dir: both
# Authorized By: Authentication Server
# Vlan Policy: 10
# Test 2: Unauthenticated device goes to guest VLAN
# Connect a device without 802.1X supplicant
# show authentication sessions interface Gi1/0/2
# Expected: Vlan Policy: 40 (Guest)
# Test 3: Failed authentication goes to quarantine
# Attempt authentication with wrong credentials
# Expected: Vlan Policy: 999 (Quarantine)
# Test 4: RADIUS server failure - critical VLAN
# Stop FreeRADIUS temporarily
# Connect a new device
# Expected: Vlan Policy: 10 (Critical/failover)
# Test 5: MAC Authentication Bypass
# Connect a printer (no supplicant)
# MAB should authenticate based on MAC address in RADIUS
# show authentication sessions interface Gi1/0/25
# Generate authentication report
# show authentication sessions | include Auth
# show dot1x all summary| Term | Definition |
|---|---|
| 802.1X | IEEE standard for port-based network access control that authenticates devices before granting network access via EAP and RADIUS |
| RADIUS | Remote Authentication Dial-In User Service protocol used by network devices to authenticate users and receive authorization attributes (VLAN, ACL) |
| MAB (MAC Authentication Bypass) | Fallback authentication method that uses a device's MAC address as credentials for devices that cannot run an 802.1X supplicant |
| EAP-PEAP | Protected Extensible Authentication Protocol that wraps EAP in a TLS tunnel, commonly used with MSCHAPv2 for username/password authentication |
| Posture Assessment | Evaluation of endpoint compliance status (OS patches, antivirus, encryption) before granting full network access |
| Dynamic VLAN Assignment | RADIUS-driven automatic VLAN placement based on user identity, group membership, or device type, eliminating static port-based VLAN configuration |
Context: A hospital needs to enforce network access control to meet HIPAA requirements. The network includes clinical workstations (domain-joined), medical devices (no 802.1X support), physician BYOD devices, and guest WiFi. The deployment must not disrupt patient care if the RADIUS server becomes unavailable.
Approach:
Pitfalls:
## NAC Deployment Report
**RADIUS Server**: freeradius-01 (10.10.100.200)
**NAC Platform**: PacketFence 13.1
**Switches Configured**: 12 access switches
**Total Ports**: 576 access ports
### Authentication Summary (24-hour)
| Auth Type | Success | Failure | Total |
|-----------|---------|---------|-------|
| 802.1X (PEAP) | 342 | 12 | 354 |
| MAB | 87 | 3 | 90 |
| Guest Portal | 23 | 5 | 28 |
### VLAN Assignment Distribution
| VLAN | Name | Assigned Devices |
|------|------|------------------|
| 10 | Corporate | 245 |
| 15 | Development | 67 |
| 20 | Finance | 30 |
| 40 | Guest | 23 |
| 50 | Medical Devices | 87 |
| 999 | Quarantine | 15 (posture fail) |
### Compliance Status
- 802.1X coverage: 100% of access ports
- Posture pass rate: 95.8% (15 devices quarantined for missing patches)
- RADIUS failover tested: Successful (critical VLAN activated in 3 seconds)© 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-network-access-control of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Implementing Network Access Control 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 Network Access Control this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.8k | Automated safety check: Notes | Apache-2.0 | |
| Policy OpaAgentSecOps/SecOpsAgentKit | 219 | 1 repos | ~3.5k | Automated safety check: Pass | Custom licence | |
| Ise Posture Auditautomateyournetwork/netclaw | 674 | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Nw Security And GovernancenWave-ai/nWave | 617 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Grc Knowledgemlunato47/claude-grc-plugin | 183 | — | ~6.1k | Automated safety check: Pass | MIT | |
| Audit Reportharness/harness-skills | 115 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
AgentSecOps/SecOpsAgentKit
Policy-as-code enforcement and compliance validation using Open Policy Agent (OPA).
automateyournetwork/netclaw
Cisco ISE posture and policy audit - authorization rules, posture compliance, profiling gaps, TrustSec SGT matrix, active session health.
nWave-ai/nWave
Database security (encryption, access control, injection prevention), data governance (lineage, quality, MDM), and compliance frameworks (GDPR, CCPA, HIPAA)
mlunato47/claude-grc-plugin
Senior GRC analyst expertise across 18 compliance frameworks — NIST 800-53, FedRAMP (Rev5 + 20x/CR26, KSIs, VDR/VER, Certification Classes A–D), DoD/DoW Impact Levels (IL2–IL6, DISA Cloud SRG), ITAR…
harness/harness-skills
Generate audit reports and compliance trails using Harness audit trail data via MCP v2 tools.
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert CIS Controls v8 (CIS Top 18) advisor — implementation group scoping (IG1/IG2/IG3), control gap assessments, safeguard-level guidance, asset inventory, software inventory, data protection…
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.
Categories
Implements 802.1X port-based network access control using RADIUS authentication, PacketFence NAC, and switch configuration to enforce identity-based access policies, posture assessment, and…. Implementing Network Access Control is an agent skill from mukul975/Anthropic-Cybersecurity-Skills.1X port-based network access control using RADIUS authentication, PacketFence NAC, and switch configuration to enforce identity-based access policies, posture assessment, and automatic VLAN assignment for authorized devices.
Implementing Network Access Control fits situations like: enforcing zero-trust access at the network edge; quarantining non-compliant endpoints; meeting PCI-DSS/HIPAA/SOC 2 access requirements; onboarding BYOD devices with automated provisioning.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-network-access-control -a claude-code`. Or copy the skill folder (skills/implementing-network-access-control in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/implementing-network-access-control in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill implementing-network-access-control -a codex`. Or copy the skill folder (skills/implementing-network-access-control in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/implementing-network-access-control 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-network-access-control -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-network-access-control, .gemini/skills/implementing-network-access-control, .github/skills/implementing-network-access-control and .opencode/skills/implementing-network-access-control in your project.
Going by SKILL.md and its folder, Implementing Network Access Control needs Python for the scripts in its folder, the command-line tools its instructions call (apt and curl) and credentials named GPG_PUBLIC_KEY. Our summary lists: Python 3; A credential in GPG_PUBLIC_KEY.
SKILL.md names 1 domain. In commands or code: inverse.ca; 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 notes only (runs commands with sudo), nothing it rates as a warning. 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 Network Access Control 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 3.8k tokens (SKILL.md is roughly 15k 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 517 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Implementing Network Access Control: Policy Opa (AgentSecOps/SecOpsAgentKit, 219 stars), Ise Posture Audit (automateyournetwork/netclaw, 674 stars), Nw Security And Governance (nWave-ai/nWave, 617 stars) and Grc Knowledge (mlunato47/claude-grc-plugin, 183 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.