AWS NAT Gateway Source Port Allocation SNAT Exhaustion Sentinel

id: aws-nat-gateway-port-allocation-error-sentinel
namespace: company.cloud

inputs:
  - id: aws_region
    type: STRING
    defaults: "us-east-1"
    description: Target AWS region.
  - id: max_error_count
    type: INT
    defaults: 0
    description: Maximum acceptable count of NAT Gateway port allocation errors over
      the last hour.

tasks:
  - id: query_nat_port_errors
    type: io.kestra.plugin.aws.cli.AwsCLI
    region: "{{ inputs.aws_region }}"
    accessKeyId: "{{ secret('AWS_ACCESS_KEY_ID') }}"
    secretKeyId: "{{ secret('AWS_SECRET_ACCESS_KEY') }}"
    commands:
      - |
        START_TIME=$(date -u -v-1H +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -d "1 hour ago" +%Y-%m-%dT%H:%M:%SZ)
        END_TIME=$(date -u +%Y-%m-%dT%H:%M:%SZ)

        aws cloudwatch get-metric-data           --metric-data-queries '[{"Id":"m1","MetricStat":{"Metric":{"Namespace":"AWS/NATGateway","MetricName":"ErrorPortAllocation"},"Period":3600,"Stat":"Sum"}}]'           --start-time "$START_TIME"           --end-time "$END_TIME"           --output json > /tmp/nat_errors.json

        ERROR_SUM=$(jq '.MetricDataResults[0].Values | add // 0' /tmp/nat_errors.json)

        echo "::set-output name=error_sum::$ERROR_SUM::"

  - id: evaluate_port_allocation
    type: io.kestra.plugin.core.flow.If
    condition: "{{ outputs.query_nat_port_errors.vars.error_sum | int >
      inputs.max_error_count }}"
    then:
      - id: notify_network_team
        type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
        url: "{{ secret('SLACK_WEBHOOK') }}"
        payload: |
          {
            "channel": "#infrastructure-alerts",
            "attachments": [
              {
                "color": "danger",
                "title": "🚨 AWS NAT Gateway Port Allocation Error (SNAT Exhaustion) Alert",
                "text": "AWS NAT Gateway recorded *{{ outputs.query_nat_port_errors.vars.error_sum }}* ErrorPortAllocation errors in region `{{ inputs.aws_region }}` over the past hour. Impact: Outbound connections from private subnets (e.g. API calls, third-party webhooks, package downloads) are being dropped due to source port exhaustion.",
                "footer": "Kestra Cloud Sentinel • AWS NAT Gateway"
              }
            ]
          }

errors:
  - id: alert_pipeline_failure
    type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
    url: "{{ secret('SLACK_WEBHOOK') }}"
    payload: |
      {
        "channel": "#infrastructure-alerts",
        "attachments": [
          {
            "color": "danger",
            "title": "⚠️ NAT Gateway Port Error Sentinel Execution Failed",
            "text": "The AWS NAT Gateway CloudWatch metric query failed. Please verify IAM permissions for cloudwatch:GetMetricData.",
            "footer": "Kestra Workflow Failure Sentinel"
          }
        ]
      }

triggers:
  - id: periodic_schedule
    type: io.kestra.plugin.core.trigger.Schedule
    cron: "*/15 * * * *"
    disabled: true