Catalog of available agents with their capabilities, metadata, and configuration, supporting versioning, lifecycle management, and controlled onboarding of new agents.
AI/ML / Multi Agent Refarch / Capabilities / DEV
Agent registry and lifecycle management
CCC.MARefArc.CP03
Related Threats
| ID | Title | Description |
|---|---|---|
| CCC.MARefArc.TH14 | Model overreach and scope creep beyond validated use | Agents are used beyond their validated scope as users discover new applications or systems are repurposed without re-evaluation, producing unreliable outputs in untested contexts; weak registry scoping and orchestration boundaries accelerate the drift. |
| CCC.MARefArc.TH31 | Multi-agent collaboration compromise | Malicious or compromised agents inject harmful data into agent-to-agent channels, contaminate shared resources, impersonate higher-privilege agents, inherit privileges through interaction, or propagate cascade failures across dependent agents. |