workspace/skills/azure-security-audit/SKILL.md
Azure NSG compliance auditing and security posture assessment. CIS Azure Foundations Benchmark rules, effective security rule analysis, orphaned NSG detection. Use when auditing Azure NSGs for CIS compliance, checking for overly permissive rules, or reviewing effective security on NICs.
npx skillsauth add automateyournetwork/netclaw azure-security-auditInstall 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.
python mcp-servers/azure-network-mcp/azure_network_mcp_server.py (stdio transport)AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET, AZURE_SUBSCRIPTION_ID| Tool | What It Does |
|------|-------------|
| azure_audit_nsg_compliance | Run CIS Azure Foundations Benchmark against all or specific NSGs |
| azure_list_nsgs | List all NSGs with orphan detection (no subnet/NIC associations) |
| azure_get_nsg_rules | Full rule list sorted by priority for a specific NSG |
| azure_get_effective_security_rules | Effective aggregated rules on a NIC (all NSGs combined) |
| Tool | What It Does |
|------|-------------|
| azure_get_network_watcher_status | Flow log configuration and retention checks |
| azure_get_vnet_details | Subnet-to-NSG associations for VNet topology context |
| azure_list_firewalls | Azure Firewall policies for layered security context |
The compliance audit checks these rules from the CIS Azure Foundations Benchmark:
| Rule | Severity | What It Checks | |------|----------|----------------| | 6.1 | Critical | RDP (port 3389) not open to 0.0.0.0/0 from internet | | 6.2 | Critical | SSH (port 22) not open to 0.0.0.0/0 from internet | | 6.3 | High | No unrestricted UDP (all ports) from internet | | 6.4 | Medium | NSG flow logs enabled with >= 90 day retention |
When asked "audit NSG compliance" or "check Azure security posture":
azure_list_nsgs -- get all NSGs, note orphaned onesazure_audit_nsg_compliance -- run CIS checks against all NSGsazure_get_nsg_rules -- review the full rule set for contextazure_get_effective_security_rules -- verify aggregated effective rulesazure_get_network_watcher_status -- check flow log coverageWhen investigating a potential security incident:
azure_get_effective_security_rules for the target NIC -- what traffic is allowed?azure_get_nsg_rules for each associated NSG -- which specific rules permit traffic?azure_audit_nsg_compliance on the specific NSG -- any known compliance gaps?azure_get_network_watcher_status -- check if flow logs captured the trafficThis skill uses tools from the same azure-network-mcp server as azure-network-ops. The skills are complementary:
Use both together for a complete Azure networking and security picture.
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
Manage EVE-NG node lifecycle. Use when listing nodes, checking runtime state, creating or deleting nodes, starting or stopping nodes or whole labs, verifying node details, or wiping node NVRAM back to factory defaults.
development
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives, checking EVE-NG health or auth, or verifying available node images before build work.
tools
Execute live CLI commands on running EVE-NG nodes over telnet console. Use when running show commands, making live config changes, verifying protocol state, testing connectivity, checking console readiness, or interacting with IOS, Junos, VPCS, EOS, or NX-OS nodes.