workspace/skills/checkpoint/SKILL.md
# Check Point Security Platform A comprehensive skill for interacting with Check Point enterprise security infrastructure through 15 MCP servers. ## Activation This skill activates when user queries involve: - Check Point firewall policies, rules, or objects - Security policy auditing or compliance - Threat intelligence (IP/URL/file reputation) - Gateway diagnostics and troubleshooting - SASE management and cloud security - Threat prevention profiles and IPS - Malware analysis and file sandbo
npx skillsauth add automateyournetwork/netclaw workspace/skills/checkpointInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A comprehensive skill for interacting with Check Point enterprise security infrastructure through 15 MCP servers.
This skill activates when user queries involve:
Explicit activation: /checkpoint prefix
This skill composes across 15 Check Point MCP servers:
| Server | Purpose | Credentials |
|--------|---------|-------------|
| chkp-management | Policies, rules, objects, topology | MGMT server |
| chkp-management-logs | Connection and audit logs | MGMT server |
| chkp-threat-prevention | TP profiles, IPS, IOC feeds | MGMT server |
| chkp-https-inspection | HTTPS inspection policies | MGMT server |
| chkp-harmony-sase | SASE regions, applications | SASE API |
| chkp-reputation-service | IP/URL/file reputation | Reputation API |
| chkp-quantum-gw-cli | Gateway diagnostics | MGMT server |
| chkp-gw-connection-analysis | Connection debugging | MGMT server |
| chkp-threat-emulation | Malware analysis | TE API |
| chkp-quantum-gaia | GAIA OS management | MGMT server |
| chkp-documentation | Check Point docs search | None |
| chkp-spark-management | Spark firewall (MSP) | Spark API |
| chkp-cpinfo-analysis | CPInfo diagnostics | None |
| chkp-argos-erm | Exposure/risk management | Argos API |
| chkp-policy-insights | Policy optimization | MGMT server |
Keywords: policy, rule, firewall, access, NAT, object, host, network, group, audit, permissive, compliance
MCP: chkp-management, chkp-policy-insights
Examples:
Keywords: logs, audit, connection, history, traffic
MCP: chkp-management-logs
Examples:
Keywords: reputation, malicious, suspicious, threat, IP, URL, hash, file, indicator
MCP: chkp-reputation-service
Examples:
Keywords: gateway, health, CPU, memory, interface, performance, status, cluster, HA
MCP: chkp-quantum-gw-cli
Gateway Selection: When multiple gateways are configured, the skill uses the first configured gateway by default. Users can specify a different gateway in their query (e.g., "show health for gateway fw-london").
Examples:
Keywords: debug, connection, failing, drops, blocked, troubleshoot, traffic
MCP: chkp-gw-connection-analysis
Examples:
Keywords: threat, IPS, protection, CVE, IOC, feed, profile, signature
MCP: chkp-threat-prevention
Examples:
Keywords: SASE, harmony, cloud, region, application, distributed
MCP: chkp-harmony-sase
Examples:
Keywords: analyze, file, malware, sandbox, emulation, verdict, suspicious
MCP: chkp-threat-emulation
Examples:
Keywords: HTTPS, SSL, inspection, decryption, certificate, bypass
MCP: chkp-https-inspection
Examples:
Keywords: GAIA, route, ARP, interface, OS, routing, table
MCP: chkp-quantum-gaia
Examples:
Keywords: docs, documentation, how, guide, reference, what is, configure, setup
MCP: chkp-documentation
Examples:
Keywords: Spark, MSP, appliance, distributed, SMB
MCP: chkp-spark-management
Examples:
Keywords: CPInfo, diagnostic, support, health check, dump
MCP: chkp-cpinfo-analysis
Examples:
Keywords: exposure, risk, vulnerability, alert, asset, ERM
MCP: chkp-argos-erm
Examples:
This skill can compose with other NetClaw skills for advanced queries:
Query logging is controlled by the CHKP_LOG_LEVEL environment variable:
| Level | Behavior |
|-------|----------|
| minimal | Log errors only |
| standard | Log queries and MCPs invoked (default) |
| verbose | Log queries, MCPs, and response summaries |
If a required MCP is not configured, the skill reports which credentials are missing and provides setup guidance.
For auth failures, the skill suggests verifying:
The skill works with partial configurations. If only Management Server credentials are set, policy and gateway queries work but SASE and Reputation queries will indicate those MCPs are unavailable.
All credentials are stored in ~/.openclaw/.env with the CHKP_ prefix:
# Management Server (on-prem)
CHKP_MGMT_HOST=192.168.1.100
CHKP_MGMT_PORT=443
CHKP_MGMT_API_KEY=your-api-key
# OR username/password:
# CHKP_MGMT_USERNAME=admin
# CHKP_MGMT_PASSWORD=your-password
CHKP_MGMT_DOMAIN= # For MDS only
# Smart-1 Cloud (alternative)
# CHKP_S1C_API_KEY=your-s1c-key
# CHKP_S1C_URL=https://tenant.maas.checkpoint.com
# Harmony SASE
CHKP_SASE_API_KEY=your-sase-key
CHKP_SASE_MGMT_HOST=https://api.us1.sase.checkpoint.com/api
CHKP_SASE_ORIGIN=https://tenant.sase.checkpoint.com
# Reputation Service
CHKP_REPUTATION_API_KEY=your-reputation-key
# Threat Emulation
CHKP_TE_API_KEY=your-te-key
# Spark (MSP)
CHKP_SPARK_API_KEY=your-spark-key
# Argos ERM
CHKP_ARGOS_API_KEY=your-argos-key
# Global
CHKP_TELEMETRY_DISABLED=true
CHKP_LOG_LEVEL=standard
Enable Check Point integration:
./scripts/checkpoint-enable.sh
Configure minimum credentials in ~/.openclaw/.env:
CHKP_MGMT_HOST=192.168.1.100
CHKP_MGMT_API_KEY=your-api-key
CHKP_TELEMETRY_DISABLED=true
Test the skill:
openclaw
> /checkpoint show my firewall policies
> /checkpoint check reputation of IP 8.8.8.8
tools
Federate your NetClaw with other NetClaw operators over the BGP mesh — exchange capability inventories and ask your claw what a peer can do. (US1; remote invocation and chat land in later phases.)
tools
3D network topology visualization and interactive digital twin in Unreal Engine 5.8 via the built-in UE5 MCP server.
testing
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
testing
IPv4 and IPv6 subnet calculator - CIDR breakdown, usable hosts, previous/next subnets, address classification, VLSM planning, and dual-stack analysis. Use when calculating subnets, figuring out how many hosts fit in a prefix, planning IP addressing, getting wildcard masks for ACLs, or checking if two IPs are in the same subnet.