Scope boundary

Owns discovery of previously unseen or newly emergent agent identities and communication edges, followed by auditable reputation and escalation findings. It does not quarantine, evict, or restore agents.

AID-D-011: AID-D-016 discovers and scores unknown or emergent agents; AID-D-011 evaluates behavior, interaction evidence, population drift, and token abuse for registered identities. Unknown-subject discovery and known-subject analytics must not share an assumed approved baseline.

Sub-techniques

• AID-D-016.001: Agent Graph Baseline & New-Agent Discovery
• AID-D-016.002: Reputation Scoring & Containment Escalation Signals

Threat mappings

MITRE ATLAS

• AML.T0103 Deploy AI Agent
• AML.T0108 AI Agent
• AML.T0118 Autonomous AI Agent Communication
• AML.T0118.001 Autonomous AI Agent Communication: Direct Agent Communication
• AML.T0124 Autonomous Attack Orchestration
• AML.T0125 Create Account

MAESTRO

• Compromised Agents (L7)
• Agent Identity Attack (L7)
• Compromised Agent Registry (L7)
• Lateral Movement (Cross-Layer)

OWASP LLM Top 10 2026

• N/A

OWASP ML Top 10 2023

• N/A

OWASP Top 10 for Agentic Applications 2026

• ASI02:2026 Tool Misuse and Exploitation
• ASI03:2026 Identity and Privilege Abuse
• ASI07:2026 Insecure Inter-Agent Communication
• ASI10:2026 Rogue Agents

NIST Adversarial Machine Learning 2025

• N/A

Cisco Integrated AI Security and Safety Framework

• AITech-4.1 Agent Injection
• AITech-4.2 Context Boundary Attacks
• AITech-5.1 Memory System Persistence
• AISubtech-4.1.1 Rogue Agent Introduction
• AISubtech-4.2.2 Session Boundary Violation
• AISubtech-5.1.1 Long-term / Short-term Memory Injection

Google Secure AI Framework 2.0 - Risks

• IIC: Insecure Integrated Component
• RA: Rogue Actions

Databricks AI Security Framework 3.0

• Agents - Core 13.7: Misaligned & Deceptive Behaviors
• Agents - Core 13.9: Identity Spoofing & Impersonation
• Agents - Core 13.13: Rogue Agents in Multi-Agent Systems