Google Model Armor
Google Cloud safety and policy layer shown in [src-043] as part of Gemini Enterprise Agent Platform ingress and egress gateways.
Key facts
- Type: AI safety / policy enforcement tool
- Ingress role: Blocks unsafe prompts such as jailbreak attempts before they reach the agent [src-043]
- Egress role: Checks outbound tool or agent calls and can block unsafe requests on the path out of an agent [src-043]
- Observability role: Emits spans and security-dashboard signals showing which interactions were flagged and why [src-043]
- Next ’26 role: Integrated inline protection inside Agent Gateway for prompt injection, tool poisoning, and sensitive data leakage [src-044]
Related entities
Related concepts
- Enterprise Agent Governance
- Agent Circuit Breakers
- Governance Observability
- Agent Forensics
- Agentic Defense