google-cloud-solution-multi-agent-security

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Gateway multi-agent security

Agent Gateway多代理安全

Critical Enforcement Rules & Rationale

关键执行规则与原理

Gcloud Release Tracks: Always use the exact release tracks specified in the commands (e.g.,
```
gcloud beta network-services agent-gateways
```
). Omitting these prefixes causes commands to fail because Agent Gateway features are located in specialized, non-default namespaces.
API Enablement: Include
```
modelarmor.googleapis.com
```
in the API enablement list when setting up guardrails. Excluding it prevents Model Armor policies and filters from successfully attaching to the Gateway.
Egress Verification: Egress policy verification requires using the Python script (scripts/verify_egress_policies.py), not
```
curl
```
. Egress gateways rely on runtime SDK lifecycle handling and JWT context that a standard curl command cannot simulate correctly.
Model Armor Keys: In
```
model-armor-config.yaml
```
, always include both
```
piAndJailbreakFilterSettings
```
and
```
sdpFilterSettings
```
(
```
filterEnforcement: ENFORCE
```
). Invalid or missing filters cause deployment validation failures or lead to silent bypasses of the guardrails.
Subnet Private Access: Any subnet hosting a Private Service Connect network attachment for Egress Gateways must have
```
private_ip_google_access = true
```
enabled in Terraform. Disabling this blocks connectivity to Google-managed endpoints, causing total routing failures for agents.
Direct Delivery: Immediately provide the requested architecture, configuration files, CLI commands, scripts, and diagrams in full. Do not stop at a planning phase, do not generate a plan artifact, and do not ask for user confirmation before delivering outputs.
No Infrastructure Execution: Do not attempt to run deployment or verification commands (such as
```
gcloud
```
,
```
kubectl
```
,
```
terraform
```
, or
```
curl
```
) against real cloud resources during design. You are generating plan configurations, not executing them.

[!IMPORTANT] Just-In-Time (JIT) Resource Loading Protocol: Inspect template files in assets/ and executable scripts in scripts/ using
view_file
as needed for extended configurations, deployment scripts, and test suites.

Gcloud发布轨道：始终使用命令中指定的精确发布轨道（例如：
```
gcloud beta network-services agent-gateways
```
）。省略这些前缀会导致命令执行失败，因为Agent Gateway功能位于专用的非默认命名空间中。
API启用：在设置防护措施时，需将
```
modelarmor.googleapis.com
```
加入API启用列表。省略该API会导致Model Armor策略和过滤器无法成功附加到网关。
出口验证：出口策略验证必须使用Python脚本（scripts/verify_egress_policies.py），而非
```
curl
```
。出口网关依赖运行时SDK生命周期处理和JWT上下文，标准curl命令无法正确模拟这些内容。
Model Armor密钥：在
```
model-armor-config.yaml
```
中，必须同时包含
```
piAndJailbreakFilterSettings
```
和
```
sdpFilterSettings
```
（
```
filterEnforcement: ENFORCE
```
）。无效或缺失的过滤器会导致部署验证失败，或导致防护措施被静默绕过。
子网私有访问：任何承载出口网关Private Service Connect网络附件的子网，必须在Terraform中启用
```
private_ip_google_access = true
```
。禁用该设置会阻止与Google托管端点的连接，导致代理完全路由失败。
直接交付：立即完整提供请求的架构、配置文件、CLI命令、脚本和图表。不要停留在规划阶段，不要生成规划工件，也不要在交付输出前请求用户确认。
禁止基础设施执行：在设计阶段，请勿尝试针对真实云资源运行部署或验证命令（如
```
gcloud
```
、
```
kubectl
```
、
```
terraform
```
或
```
curl
```
）。你需要生成的是规划配置，而非执行它们。

[!IMPORTANT] 即时（JIT）资源加载协议：如需扩展配置、部署脚本和测试套件，可使用
view_file
查看assets/中的模板文件和scripts/中的可执行脚本。

Quick Reference: Required Filenames

快速参考：必填文件名

Always generate files with these exact names when requested:

```
agw-ingress-config.yaml
```
(assets/agw-ingress-config.yaml)
```
agw-egress-config.yaml
```
(assets/agw-egress-config.yaml)
```
agw-authz-extension.yaml
```
(assets/agw-authz-extension.yaml)
```
agw-authz-policy.yaml
```
(assets/agw-authz-policy.yaml)
```
model-armor-config.yaml
```
(assets/model-armor-config.yaml)
```
sgp-policy.yaml
```
(assets/sgp-policy.yaml)
```
iap-policy.json
```
(assets/iap-policy.json)
```
model-armor-payload.json
```
(assets/model-armor-payload.json)

当被请求时，必须生成以下精确名称的文件：

```
agw-ingress-config.yaml
```
（assets/agw-ingress-config.yaml）
```
agw-egress-config.yaml
```
（assets/agw-egress-config.yaml）
```
agw-authz-extension.yaml
```
（assets/agw-authz-extension.yaml）
```
agw-authz-policy.yaml
```
（assets/agw-authz-policy.yaml）
```
model-armor-config.yaml
```
（assets/model-armor-config.yaml）
```
sgp-policy.yaml
```
（assets/sgp-policy.yaml）
```
iap-policy.json
```
（assets/iap-policy.json）
```
model-armor-payload.json
```
（assets/model-armor-payload.json）

1. Dual Ingress & Egress Architecture Design (

dual_ingress_egress_architecture_design

)

1. 双入口与出口架构设计（

dual_ingress_egress_architecture_design

）

Ingress Pattern:
```
CLIENT_TO_AGENT
```
fronted by Ingress Control Plane (Agent Gateway, Model Armor).
Egress Pattern:
```
AGENT_TO_ANYWHERE
```
utilizing Egress Control Plane (Agent Gateway,
```
roles/iap.egressor
```
CEL policies, Cloud DNS) and Egress Data Plane (PSC Interface, Cloud Run, PSC Google APIs Global Endpoint), coordinated via Agent Registry & Agent Engine runtime.

Mermaid Diagram:

mermaid

graph TD
    Client["External Clients"] -->|HTTPS / MCP| GLB["Global Load Balancer"]
    GLB --> Ingress["Ingress Agent Gateway (CLIENT_TO_AGENT)"]
    Ingress --> MA["Model Armor (CONTENT_AUTHZ)"]
    MA --> Agent["Agent Engine Agents (BillingAgent, SupportAgent, FraudAgent)"]
    Agent --> Egress["Egress Agent Gateway (AGENT_TO_ANYWHERE)"]
    Egress --> PSC["Private Service Connect Network Attachment"]
    PSC --> Tools["Private MCP Tool Backends"]

入口模式：由入口控制平面（Agent Gateway、Model Armor）提供支持的
```
CLIENT_TO_AGENT
```
。
出口模式：利用出口控制平面（Agent Gateway、
```
roles/iap.egressor
```
CEL策略、Cloud DNS）和出口数据平面（PSC接口、Cloud Run、PSC Google APIs全局端点）的
```
AGENT_TO_ANYWHERE
```
，通过Agent Registry和Agent Engine运行时进行协调。

Mermaid图表：

mermaid

graph TD
    Client["External Clients"] -->|HTTPS / MCP| GLB["Global Load Balancer"]
    GLB --> Ingress["Ingress Agent Gateway (CLIENT_TO_AGENT)"]
    Ingress --> MA["Model Armor (CONTENT_AUTHZ)"]
    MA --> Agent["Agent Engine Agents (BillingAgent, SupportAgent, FraudAgent)"]
    Agent --> Egress["Egress Agent Gateway (AGENT_TO_ANYWHERE)"]
    Egress --> PSC["Private Service Connect Network Attachment"]
    PSC --> Tools["Private MCP Tool Backends"]

2. Ingress & Egress Guardrail Policy Config (

ingress_and_egress_guardrail_policy_config

)

2. 入口与出口防护策略配置（

ingress_and_egress_guardrail_policy_config

）

When requested for Ingress & Egress guardrail policy configs, you MUST generate and create all required files in the workspace:

agw-ingress-config.yaml

(assets/agw-ingress-config.yaml): Declares

governedAccessPath: CLIENT_TO_AGENT

with protocols

HTTP

and

MCP

agw-egress-config.yaml

(assets/agw-egress-config.yaml): Declares

governedAccessPath: AGENT_TO_ANYWHERE

with protocol

MCP

```
agw-authz-extension.yaml
```
(assets/agw-authz-extension.yaml): Configures AuthzExtension service for IAP authorization.
```
agw-authz-policy.yaml
```
(assets/agw-authz-policy.yaml): Configures
```
AuthzPolicy
```
action
```
ALLOW
```
targeting both Ingress and Egress gateways.

iap-policy.json

(assets/iap-policy.json): Binds

roles/iap.egressor

with CEL condition checking

iap.googleapis.com/mcp.toolName == 'get_account_balance' && iap.googleapis.com/mcp.tool.isReadOnly == true

model-armor-config.yaml

(assets/model-armor-config.yaml): Enables

piAndJailbreakFilterSettings

and

sdpFilterSettings

with

filterEnforcement: ENFORCE

```
sgp-policy.yaml
```
(assets/sgp-policy.yaml): Implements Natural Language Constraints blocking transactions > $1000 and sanitizing PII.

当被请求提供入口与出口防护策略配置时，必须在工作区中生成并创建所有必填文件：

```
agw-ingress-config.yaml
```
（assets/agw-ingress-config.yaml）：声明
```
governedAccessPath: CLIENT_TO_AGENT
```
，支持
```
HTTP
```
和
```
MCP
```
协议。

agw-egress-config.yaml

（assets/agw-egress-config.yaml）：声明

governedAccessPath: AGENT_TO_ANYWHERE

，支持

MCP

协议。

```
agw-authz-extension.yaml
```
（assets/agw-authz-extension.yaml）：配置AuthzExtension服务以实现IAP授权。
```
agw-authz-policy.yaml
```
（assets/agw-authz-policy.yaml）：配置针对入口和出口网关的
```
AuthzPolicy
```
允许动作。

iap-policy.json

（assets/iap-policy.json）：绑定

roles/iap.egressor

，并添加CEL条件检查

iap.googleapis.com/mcp.toolName == 'get_account_balance' && iap.googleapis.com/mcp.tool.isReadOnly == true

。

model-armor-config.yaml

（assets/model-armor-config.yaml）：启用

piAndJailbreakFilterSettings

和

sdpFilterSettings

，并设置

filterEnforcement: ENFORCE

。

```
sgp-policy.yaml
```
（assets/sgp-policy.yaml）：实现自然语言约束，阻止超过1000美元的交易并清理PII数据。

3. Ingress & Egress Infrastructure Deployment (

ingress_and_egress_infrastructure_deployment

)

3. 入口与出口基础设施部署（

ingress_and_egress_infrastructure_deployment

）

Inspect and provide the step-by-step

gcloud

CLI commands from scripts/deploy_infrastructure.sh:

Enable Required APIs:

compute

networkservices

networksecurity

modelarmor

iap

agentregistry

serviceextensions

, and

aiplatform

Import Agent Gateways: Ingress (

agw-ingress-config.yaml

) and Egress (

agw-egress-config.yaml

) via

gcloud alpha network-services agent-gateways import

Import Authz Extension:

agw-authz-extension.yaml

via

gcloud beta service-extensions authz-extensions import

Import Authz Policy:

agw-authz-policy.yaml

via

gcloud beta network-security authz-policies import

查看并提供scripts/deploy_infrastructure.sh中的分步

gcloud

CLI命令：

启用必填API：

compute

、

networkservices

、

networksecurity

、

modelarmor

、

iap

、

agentregistry

、

serviceextensions

和

aiplatform

。

导入Agent网关：通过

gcloud alpha network-services agent-gateways import

导入入口（

agw-ingress-config.yaml

）和出口（

agw-egress-config.yaml

）网关。

导入授权扩展：通过

gcloud beta service-extensions authz-extensions import

导入

agw-authz-extension.yaml

。

导入授权策略：通过

gcloud beta network-security authz-policies import

导入

agw-authz-policy.yaml

。

4. Ingress & Egress Security Validation (

ingress_and_egress_security_validation

)

4. 入口与出口安全验证（

ingress_and_egress_security_validation

）

When validating security for Ingress and Egress:

Ingress 403 Unauthenticated Test: Provide the copy-pasteable verification curl command from scripts/validate_ingress_unauth.sh sending an unauthenticated POST request to the Reasoning Engine endpoint expecting HTTP 403 Forbidden.
Python Egress Verification Script (MUST use Python script snippet, NOT curl): Provide the Python verification script snippet from scripts/verify_egress_policies.py sending JSON-RPC
```
tools/call
```
requests (
```
get_account_balance
```
) through the Egress Gateway to verify HTTP 200 for allowed tools.
Model Armor Test Payload: Generate
```
model-armor-payload.json
```
(assets/model-armor-payload.json) containing prompt injection/jailbreak instructions.

验证入口和出口安全性时：

入口未认证403测试：提供scripts/validate_ingress_unauth.sh中的可复制验证curl命令，向推理引擎端点发送未认证POST请求，预期返回HTTP 403 Forbidden。
Python出口验证脚本（必须使用Python代码片段，而非curl）：提供scripts/verify_egress_policies.py中的Python验证代码片段，通过出口网关发送JSON-RPC
```
tools/call
```
请求（
```
get_account_balance
```
），验证允许的工具返回HTTP 200。
Model Armor测试负载：生成包含提示注入/越狱指令的
```
model-armor-payload.json
```
（assets/model-armor-payload.json）。

5. Troubleshooting Ingress & Egress Failures (

troubleshooting_ingress_and_egress_failures

)

5. 入口与出口故障排查（

troubleshooting_ingress_and_egress_failures

）

Ingress 403 (Client-to-Agent):
- Root Cause: Unauthenticated client requests or missing/invalid OAuth 2.0 / IAP identity tokens.
- OAuth Configuration Steps:
  1. Configure OAuth 2.0 Client ID credentials in Google Cloud Console.
  2. Grant the client identity / service account
```
roles/iap.httpsResourceAccessor
```
    permission.
  3. Exchange credentials with Google OAuth to acquire an OIDC / OAuth ID token.
  4. Pass the token in the
```
Authorization: Bearer <TOKEN>
```
    header.
- Verification Command: Provide the curl command from scripts/verify_ingress_auth.sh.
Egress 403 (Agent-to-Anywhere):
- Root Cause: Missing
```
roles/iap.egressor
```
  IAM bindings on the Agent Identity, malformed principal ID, or mismatched CEL condition on tool metadata.
- Fix Command: Provide the exact
```
gcloud
```
  command from scripts/fix_egress_iap.sh.

入口403错误（客户端到代理）：
- 根本原因：未认证的客户端请求，或缺失/无效的OAuth 2.0 / IAP身份令牌。
- OAuth配置步骤：
  1. 在Google Cloud控制台中配置OAuth 2.0客户端ID凭据。
  2. 为客户端身份/服务账号授予
```
roles/iap.httpsResourceAccessor
```
    权限。
  3. 与Google OAuth交换凭据以获取OIDC / OAuth ID令牌。
  4. 在
```
Authorization: Bearer <TOKEN>
```
    请求头中传递该令牌。
- 验证命令：提供scripts/verify_ingress_auth.sh中的curl命令。
出口403错误（代理到任意地址）：
- 根本原因：代理身份缺失
```
roles/iap.egressor
```
  IAM绑定、主体ID格式错误，或工具元数据的CEL条件不匹配。
- 修复命令：提供scripts/fix_egress_iap.sh中的精确
```
gcloud
```
  命令。

6. Hybrid VPN Connectivity & Egress Routing (

hybrid_vpn_connectivity_egress_routing

)

6. 混合VPN连接与出口路由（

hybrid_vpn_connectivity_egress_routing

）

Terraform HCL: Refer to baseline Terraform config in assets/main.tf for VPC, subnets (
```
private_ip_google_access = true
```
), PSC network attachment, Cloud DNS private forwarding for
```
aws.internal.
```
, and HA VPN gateway/router.
Egress Gateway Config (
agw-egress-config.yaml
): Generate configuration declaring
```
governedAccessPath: AGENT_TO_ANYWHERE
```
, pointing to the PSC network attachment, and referencing
```
aws.internal.
```
in
```
dnsPeeringConfig
```
(see assets/agw-egress-config.yaml).
Python SDK Deployment Script: Refer to scripts/hybrid_vpn_agent.py for the complete script initializing Vertex AI with
```
agent_to_anywhere_config
```
referencing the Egress Gateway, enabling telemetry, and deploying
```
HybridAgent
```
using
```
types.IdentityType.AGENT_IDENTITY
```
.

Terraform HCL：参考assets/main.tf中的基线Terraform配置，包含VPC、子网（
```
private_ip_google_access = true
```
）、PSC网络附件、针对
```
aws.internal.
```
的Cloud DNS私有转发，以及HA VPN网关/路由器。
出口网关配置（
agw-egress-config.yaml
）：生成声明
```
governedAccessPath: AGENT_TO_ANYWHERE
```
的配置，指向PSC网络附件，并在
```
dnsPeeringConfig
```
中引用
```
aws.internal.
```
（见assets/agw-egress-config.yaml）。
Python SDK部署脚本：参考scripts/hybrid_vpn_agent.py中的完整脚本，该脚本初始化Vertex AI，使用引用出口网关的
```
agent_to_anywhere_config
```
，启用遥测，并使用
```
types.IdentityType.AGENT_IDENTITY
```
部署
```
HybridAgent
```
。

7. Private Egress GKE Internal Load Balancer (

private_egress_gke_internal_load_balancer

)

7. 私有出口GKE内部负载均衡器（

private_egress_gke_internal_load_balancer

）

Expose GKE internal MCP tool server via an Internal Load Balancer (ILB) at literal IP
```
10.0.1.50
```
, connecting via Agent Gateway PSC Interface + Cloud DNS Private zone.
Cloud DNS Record Mapping: Provide the command from scripts/create_gke_dns_record.sh mapping the private domain to GKE's private ILB IP
```
10.0.1.50
```
.
Explicit TLS Warning: Agent Gateway egress does not natively trust self-signed certificates or private enterprise CAs. You must use publicly trusted TLS certificates signed by a trusted Certificate Authority (e.g., Let's Encrypt).

通过内部负载均衡器（ILB）暴露GKE内部MCP工具服务器，固定IP为
```
10.0.1.50
```
，通过Agent Gateway PSC接口+Cloud DNS私有区域连接。
Cloud DNS记录映射：提供scripts/create_gke_dns_record.sh中的命令，将私有域映射到GKE的私有ILB IP
```
10.0.1.50
```
。
明确TLS警告：Agent Gateway出口不原生信任自签名证书或私有企业CA。你必须使用受信任证书颁发机构（如Let's Encrypt）签名的公开可信TLS证书。

8. Governance Controls Model Armor SGP (

governance_controls_model_armor_sgp

)

8. 治理控制Model Armor SGP（

governance_controls_model_armor_sgp

）

When configuring dual safety layers with Model Armor on Ingress and SGP on Egress:

Model Armor Config: Generate

model-armor-config.yaml

(assets/model-armor-config.yaml) with

piAndJailbreakFilterSettings

and

sdpFilterSettings

(

filterEnforcement: ENFORCE

Semantic Governance Policy: Generate
```
sgp-policy.yaml
```
(assets/sgp-policy.yaml) with Natural Language Constraints blocking transactions > $1000 and sanitizing PII.
Curl PATCH Command: Provide the curl command from scripts/enforce_sgp_patch.sh to update
```
authzExtensions
```
with
```
sgpEnforcementMode
```
set to
```
ENFORCE
```
.

在入口配置Model Armor、在出口配置SGP的双重安全层时：

Model Armor配置：生成包含

piAndJailbreakFilterSettings

和

sdpFilterSettings

（

filterEnforcement: ENFORCE

）的

model-armor-config.yaml

（assets/model-armor-config.yaml）。

语义治理策略：生成包含自然语言约束（阻止超过1000美元的交易并清理PII数据）的
```
sgp-policy.yaml
```
（assets/sgp-policy.yaml）。
curl PATCH命令：提供scripts/enforce_sgp_patch.sh中的curl命令，将
```
authzExtensions
```
更新为
```
sgpEnforcementMode: ENFORCE
```
。

9. Multi-Agent Cloud Run Egress Routing (

multi_agent_cloud_run_egress_routing

)

9. 多代理Cloud Run出口路由（

multi_agent_cloud_run_egress_routing

）

Do NOT produce a plan artifact or stop at planning. When configuring multi-agent Cloud Run egress routing, you MUST directly provide and generate ALL required components:

Egress Gateway Config (
agw-egress-config-run.yaml
): Generate configuration declaring
```
governedAccessPath: AGENT_TO_ANYWHERE
```
, PSC network attachment, and DNS peering for
```
*.run.app
```
(see assets/agw-egress-config-run.yaml).
Register Cloud Run Services in Agent Registry: Provide the registration commands from scripts/register_cloud_run_services.sh registering all 3 Cloud Run services (
```
marketing-tool-service
```
,
```
sales-tool-service
```
,
```
support-tool-service
```
) in the
```
us-east4
```
Agent Registry.
iap-policy.json
(Multi-Agent): Generate
```
iap-policy.json
```
(assets/iap-policy-multi-agent.json) containing all 3
```
principal://
```
bindings in the
```
members
```
list under
```
roles/iap.egressor
```
.
Python SDK Deployment Script: Refer to scripts/multi_agent_cloud_run.py for the complete GenAI SDK deployment script.

请勿生成规划工件或停留在规划阶段。配置多代理Cloud Run出口路由时，必须直接提供并生成所有必填组件：

出口网关配置（
agw-egress-config-run.yaml
）：生成声明
```
governedAccessPath: AGENT_TO_ANYWHERE
```
、PSC网络附件，以及针对
```
*.run.app
```
的DNS peering配置（见assets/agw-egress-config-run.yaml）。
在Agent Registry中注册Cloud Run服务：提供scripts/register_cloud_run_services.sh中的注册命令，在
```
us-east4
```
区域的Agent Registry中注册所有3个Cloud Run服务（
```
marketing-tool-service
```
、
```
sales-tool-service
```
、
```
support-tool-service
```
）。
多代理
iap-policy.json
：生成包含
```
roles/iap.egressor
```
下
```
members
```
列表中所有3个
```
principal://
```
绑定的
```
iap-policy.json
```
（assets/iap-policy-multi-agent.json）。
Python SDK部署脚本：参考scripts/multi_agent_cloud_run.py中的完整GenAI SDK部署脚本。

10. Advanced Model Armor Filtering (

advanced_model_armor_filtering

)

10. 高级Model Armor过滤（

advanced_model_armor_filtering

）

For custom keyword matching, configure

userDefinedFilterSettings

(see assets/model-armor-advanced.yaml).

如需自定义关键词匹配，可配置

userDefinedFilterSettings

（见assets/model-armor-advanced.yaml）。

11. Known Traps & Gotchas (

known_traps_and_gotchas

)

11. 已知陷阱与注意事项（

known_traps_and_gotchas

）

network_attachment
is
ForceNew
: Enabling Semantic Governance Policies (SGP) or modifying network attachments after the initial Terraform apply will force-recreate the gateway resource. If not managed carefully, this can cause dependency deadlocks during destroy operations. Plan infrastructure sequencing accordingly.
Authz Policy Limit: An Agent Gateway allows at most 4 custom authorization policies attached concurrently. Ensure your security posture consolidates rules within this limit.

network_attachment
为
ForceNew
类型：在初始Terraform应用后启用语义治理策略（SGP）或修改网络附件，会强制重新创建网关资源。如果管理不当，这可能会在销毁操作期间导致依赖死锁。请相应规划基础设施的部署顺序。
授权策略限制：一个Agent Gateway最多允许同时附加4个自定义授权策略。请确保你的安全策略在该限制内整合规则。

google-cloud-solution-multi-agent-security

Original

Translation

Agent Gateway multi-agent security

Agent Gateway多代理安全

Critical Enforcement Rules & Rationale

关键执行规则与原理

Quick Reference: Required Filenames

快速参考：必填文件名

1. Dual Ingress & Egress Architecture Design (
`dual_ingress_egress_architecture_design`
)

1. 双入口与出口架构设计（
`dual_ingress_egress_architecture_design`
）

2. Ingress & Egress Guardrail Policy Config (
`ingress_and_egress_guardrail_policy_config`
)

2. 入口与出口防护策略配置（
`ingress_and_egress_guardrail_policy_config`
）

3. Ingress & Egress Infrastructure Deployment (
`ingress_and_egress_infrastructure_deployment`
)

3. 入口与出口基础设施部署（
`ingress_and_egress_infrastructure_deployment`
）

4. Ingress & Egress Security Validation (
`ingress_and_egress_security_validation`
)

4. 入口与出口安全验证（
`ingress_and_egress_security_validation`
）

5. Troubleshooting Ingress & Egress Failures (
`troubleshooting_ingress_and_egress_failures`
)

5. 入口与出口故障排查（
`troubleshooting_ingress_and_egress_failures`
）

6. Hybrid VPN Connectivity & Egress Routing (
`hybrid_vpn_connectivity_egress_routing`
)

6. 混合VPN连接与出口路由（
`hybrid_vpn_connectivity_egress_routing`
）

7. Private Egress GKE Internal Load Balancer (
`private_egress_gke_internal_load_balancer`
)

7. 私有出口GKE内部负载均衡器（
`private_egress_gke_internal_load_balancer`
）

8. Governance Controls Model Armor SGP (
`governance_controls_model_armor_sgp`
)

8. 治理控制Model Armor SGP（
`governance_controls_model_armor_sgp`
）

9. Multi-Agent Cloud Run Egress Routing (
`multi_agent_cloud_run_egress_routing`
)

9. 多代理Cloud Run出口路由（
`multi_agent_cloud_run_egress_routing`
）

10. Advanced Model Armor Filtering (
`advanced_model_armor_filtering`
)

10. 高级Model Armor过滤（
`advanced_model_armor_filtering`
）

11. Known Traps & Gotchas (
`known_traps_and_gotchas`
)

11. 已知陷阱与注意事项（
`known_traps_and_gotchas`
）

google-cloud-solution-multi-agent-security

Original

Translation

Agent Gateway multi-agent security

Agent Gateway多代理安全

Critical Enforcement Rules & Rationale

关键执行规则与原理

Quick Reference: Required Filenames

快速参考：必填文件名

1. Dual Ingress & Egress Architecture Design (dual_ingress_egress_architecture_design)

1. 双入口与出口架构设计（dual_ingress_egress_architecture_design）

2. Ingress & Egress Guardrail Policy Config (ingress_and_egress_guardrail_policy_config)

2. 入口与出口防护策略配置（ingress_and_egress_guardrail_policy_config）

3. Ingress & Egress Infrastructure Deployment (ingress_and_egress_infrastructure_deployment)

3. 入口与出口基础设施部署（ingress_and_egress_infrastructure_deployment）

4. Ingress & Egress Security Validation (ingress_and_egress_security_validation)

4. 入口与出口安全验证（ingress_and_egress_security_validation）

5. Troubleshooting Ingress & Egress Failures (troubleshooting_ingress_and_egress_failures)

5. 入口与出口故障排查（troubleshooting_ingress_and_egress_failures）

6. Hybrid VPN Connectivity & Egress Routing (hybrid_vpn_connectivity_egress_routing)

6. 混合VPN连接与出口路由（hybrid_vpn_connectivity_egress_routing）

7. Private Egress GKE Internal Load Balancer (private_egress_gke_internal_load_balancer)

7. 私有出口GKE内部负载均衡器（private_egress_gke_internal_load_balancer）

8. Governance Controls Model Armor SGP (governance_controls_model_armor_sgp)

8. 治理控制Model Armor SGP（governance_controls_model_armor_sgp）

9. Multi-Agent Cloud Run Egress Routing (multi_agent_cloud_run_egress_routing)

9. 多代理Cloud Run出口路由（multi_agent_cloud_run_egress_routing）

10. Advanced Model Armor Filtering (advanced_model_armor_filtering)

10. 高级Model Armor过滤（advanced_model_armor_filtering）

11. Known Traps & Gotchas (known_traps_and_gotchas)

11. 已知陷阱与注意事项（known_traps_and_gotchas）

1. Dual Ingress & Egress Architecture Design (
`dual_ingress_egress_architecture_design`
)

1. 双入口与出口架构设计（
`dual_ingress_egress_architecture_design`
）

2. Ingress & Egress Guardrail Policy Config (
`ingress_and_egress_guardrail_policy_config`
)

2. 入口与出口防护策略配置（
`ingress_and_egress_guardrail_policy_config`
）

3. Ingress & Egress Infrastructure Deployment (
`ingress_and_egress_infrastructure_deployment`
)

3. 入口与出口基础设施部署（
`ingress_and_egress_infrastructure_deployment`
）

4. Ingress & Egress Security Validation (
`ingress_and_egress_security_validation`
)

4. 入口与出口安全验证（
`ingress_and_egress_security_validation`
）

5. Troubleshooting Ingress & Egress Failures (
`troubleshooting_ingress_and_egress_failures`
)

5. 入口与出口故障排查（
`troubleshooting_ingress_and_egress_failures`
）

6. Hybrid VPN Connectivity & Egress Routing (
`hybrid_vpn_connectivity_egress_routing`
)

6. 混合VPN连接与出口路由（
`hybrid_vpn_connectivity_egress_routing`
）

7. Private Egress GKE Internal Load Balancer (
`private_egress_gke_internal_load_balancer`
)

7. 私有出口GKE内部负载均衡器（
`private_egress_gke_internal_load_balancer`
）

8. Governance Controls Model Armor SGP (
`governance_controls_model_armor_sgp`
)

8. 治理控制Model Armor SGP（
`governance_controls_model_armor_sgp`
）

9. Multi-Agent Cloud Run Egress Routing (
`multi_agent_cloud_run_egress_routing`
)

9. 多代理Cloud Run出口路由（
`multi_agent_cloud_run_egress_routing`
）

10. Advanced Model Armor Filtering (
`advanced_model_armor_filtering`
)

10. 高级Model Armor过滤（
`advanced_model_armor_filtering`
）

11. Known Traps & Gotchas (
`known_traps_and_gotchas`
)

11. 已知陷阱与注意事项（
`known_traps_and_gotchas`
）