WAF++ WAF++

WAF-AGN-060 – Multi-Agent Orchestration

Pillar: Agentic | Severity: Medium | Category: Orchestration | Automatable: Medium

Description

Many agents must be coordinated. Agent orchestration must use coordinator/manager patterns or mesh architectures. Event-based communication must be configured for agent messaging. Failure recovery and agent health monitoring must be in place.

Rationale

Uncoordinated multi-agent systems create several problems:

Redundant work: Multiple agents working on same task without coordination wastes resources.

Conflicting actions: Agents may take contradictory actions without coordination.

Performance issues: Lack of load balancing causes some agents to overload while others idle.

Failure propagation: When one agent fails, dependent agents may also fail without recovery.

No visibility: Hard to monitor overall system health without orchestration.

Requirements

  • Coordinator/manager pattern must be used for agent orchestration

  • Event-based communication (SNS, SQS, EventBridge) must be configured

  • Failure recovery mechanisms must be in place

  • Agent health monitoring must be configured

  • Dead letter queues must be configured for failed messages

Implementation Guidance

  1. Design coordinator pattern: One manager agent delegates tasks to specialized workers

  2. Use event channels: Configure SNS topics, SQS queues, and EventBridge rules

  3. Implement retry logic: Configure message retries with exponential backoff

  4. Set up dead letter queues: Configure DLQ for messages that fail repeatedly

  5. Monitor agent health: Configure alarms for agent failures and latency spikes

Maturity Levels

Level Name Criteria

1

No Orchestration

Agents operate independently without coordination. No failover.

2

Manual Coordination

Some manual orchestration via external systems.

3

Event-Based Coordination

Agents communicate via events. Basic failover configured.

4

Automated Orchestration

Dynamic task allocation. Automatic failover and scaling.

5

Self-Healing System

Orchestrator learns from failures and improves automatically.

Terraform Checks

waf-agn-060.tf.aws.coordinator-agent-configured

Checks: Multi-agent systems have coordinator/manager configured.

Compliant Non-Compliant 
resource "aws_bedrockagent" "coordinator" {
  agent_name = "agent-coordinator"
  # Manages multiple worker agents
}

resource "aws_bedrockagent" "worker_analysis" {
  agent_name = "analysis-worker"
  # Works under coordinator direction
}

resource "aws_bedrockagent" "worker_research" {
  agent_name = "research-worker"
  # Works under coordinator direction
}

resource "aws_lambda_function" "agent_coordinator" {
  function_name = "agent-coordinator-function"
  # Coordinates agent communication
}

No coordinator defined

waf-agn-060.tf.aws.event-based-communication

Checks: Agent communication uses event-based messaging (SNS, SQS, EventBridge).

# Compliant
resource "aws_sns_topic" "agent_events" {
  name = "agent-events"
}

resource "aws_sqs_queue" "agent_queue" {
  name = "agent-messages"
}

resource "aws_sns_topic_subscription" "agent_subscription" {
  topic_arn = aws_sns_topic.agent_events.arn
  protocol  = "sqs"
  endpoint  = aws_sqs_queue.agent_queue.arn
}

resource "aws_bedrockagent" "event_agent" {
  agent_name = "event-based-agent"
}

Remediation: Configure coordinator agent pattern. Set up event-based messaging via SNS/SQS. Implement failure recovery with DLQs and alarms.

Evidence

Type Required Description

IaC

✅ Required

Coordinator agent configuration, event channel setup, DLQ configuration.

Config

✅ Required

Queue configurations, retry policies, alarm thresholds.

Process

✅ Required

Orchestration runbook, failover test reports, health monitoring dashboards.

Governance

✅ Required

Multi-agent orchestration policy defining coordination requirements.

Related Controls

Regulatory Mapping

Framework Controls

ISO 27001:2022

A.8.1 – Information security roles and responsibilities; A.8.2 – Privileged access rights

NIST SP 800-53

AU-2 – Event logging; AU-6 – Audit review and analysis

NIST CSF 2.0

DE.CM – Continuous monitoring; DE.DP – Data protection

GDPR

Art. 32 – Security of processing; Art. 5(1)(f) – Integrity and confidentiality

PCI DSS v4.0

Req 10 – Monitor and detect threats

TISAX

Information security – Monitoring and logging

ANSSI SecNumCloud

Domain – Logging and monitoring

BIO

BIO – Logboekhouding en monitoring

ENS High

op.exp.6 – Gestión de cambios

UK NCSC CAF

A4 – Policy and assurance

FedRAMP

AU-2, AU-6 (Moderate baseline)

CMMC 2.0

AU.L2-3.8.1 – Flow audit logs to central log management

IT-Grundschutz

ORP.1 – Informationstechnisch-related Angriffsschutz

IRAP

ISM – Logging and monitoring

CCCS PBMM

AU-2, AU-6 – Logging and audit

MAS TRM

Ch.9 – Change management

ISMAP

Monitoring and logging controls

FISC

Technical measures – Logging and monitoring

AWS Well-Architected Framework

Security Pillar – Logging and monitoring; Reliability Pillar – Failure management

Google Cloud Architecture Framework

Reliability – Failure management; Security – Monitoring

BSI C5:2020

OPS-01 – Operational monitoring

SOC 2 Type II

CC4.1 – Monitoring activities; CC7.1 – Infrastructure and software monitoring

CSA STAR

CCM Logging and Monitoring

CIS Controls v8

CIS 13 – Content Filtering