google-cloud-solution-multi-agent-security
Designs, deploys, and secures Google Cloud Agent Gateway solutions.
Skill by googleOfficial
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/google-google-cloud-solution-multi-agent-security
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: cloud, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/google-cloud-solution-multi-agent-security
What's inside
- Skill name
google-cloud-solution-multi-agent-security- Description
- Designs, deploys, and secures Google Cloud Agent Gateway solutions. Use when the user needs to configure multi-agent security, ingress (CLIENT_TO_AGENT), or egress (AGENT_TO_ANYWHERE) patterns involving Model Armor, IAP, and Agent Registry. Don't use for general Cloud Load Balancing or basic VPC setup not related to Agent Gateways.
- License
- Apache-2.0
- Metadata
- version: 1.0.1 · category: MultiProductSolutions
- Instructions
- 280 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions call the network
Files (24)
- SKILL.md
- agw-authz-extension.yaml · assets/
- agw-authz-policy.yaml · assets/
- agw-egress-config-run.yaml · assets/
- agw-egress-config.yaml · assets/
- agw-ingress-config.yaml · assets/
- iap-policy-multi-agent.json · assets/
- iap-policy.json · assets/
- main.tf · assets/
- model-armor-advanced.yaml · assets/
- model-armor-config.yaml · assets/
- model-armor-payload.json · assets/
- sgp-policy.yaml · assets/
- attribution.md · references/
- create_gke_dns_record.sh · scripts/
- deploy_infrastructure.sh · scripts/
- enforce_sgp_patch.sh · scripts/
- fix_egress_iap.sh · scripts/
- hybrid_vpn_agent.py · scripts/
- multi_agent_cloud_run.py · scripts/
- register_cloud_run_services.sh · scripts/
- validate_ingress_unauth.sh · scripts/
- verify_egress_policies.py · scripts/
- verify_ingress_auth.sh · scripts/
SKILL.md (first lines)
# Agent Gateway multi-agent security
## Attribution
**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you
MUST read and follow the instructions in
[Usage Attribution](references/attribution.md).
## Critical Enforcement Rules & Rationale
* **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](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/](assets/) and executable scripts in
> [scripts/](scripts/) using `view_file` as needed for extended configurations,
> deployment scripts, and test suites.
--------------------------------------------------------------------------------
## Quick Reference: Required Filenames
Always generate files with these exact names when requested:
1. `agw-ingress-config.yaml`
([assets/agw-ingress-config.yaml](assets/agw-ingress-config.yaml))
2. `agw-egress-config.yaml`
([assets/agw-egress-config.yaml](assets/agw-egress-config.yaml))
3. `agw-authz-extension.yaml`
([assets/agw-authz-extension.yaml](assets/agw-authz-extension.yaml))
4. `agw-authz-policy.yaml`
([assets/agw-authz-policy.yaml](assets/agw-authz-policy.yaml))
5. `model-armor-config.yaml`
([assets/model-armor-config.yaml](assets/model-armor-config.yaml))
6. `sgp-policy.yaml` ([assets/sgp-policy.yaml](assets/sgp-policy.yaml))
7. `iap-policy.json` ([assets/iap-policy.json](assets/iap-policy.json))
8. `model-armor-payload.json`
([assets/model-armor-payload.json](assets/model-armor-payload.json))
--------------------------------------------------------------------------------
## 1. Dual Ingress & Egress Architecture Design (`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"]
```
--------------------------------------------------------------------------------
## 2. Ingress & Egress Guardrail Policy Config (`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](assets/agw-ingress-config.yaml)): Declares
`governedAccessPath: CLIENT_TO_AGENT` with protocols `HTTP` and `MCP`.
- `agw-egress-config.yaml`
([assets/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](assets/agw-authz-extension.yaml)):
Configures AuthzExtension service for IAP authorization.
- `agw-authz-policy.yaml`
([assets/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](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](assets/model-armor-config.yaml)): Enables
`piAndJailbreakFilterSettings` and `sdpFilterSettings` with
`filterEnforcement: ENFORCE`.
- `sgp-policy.yaml` ([assets/sgp-policy.yaml](assets/sgp-policy.yaml)):
Implements Natural Language Constraints blocking transactions > $1000 and
sanitizing PII.From google/skills, Apache-2.0.
More from google/skills
- 0.865score
google-ads-api-account-diagnostics
google-ads-api-teamOfficial
Diagnoses Google Ads account performance issues such as conversion loss (value or volume), low lead flow/volume, and lost impression share (opportunities) due…
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.861score
secops-triage
Google LLCOfficial
Expert guidance for security alert triage in Google SecOps.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.861score
secops-detection-engineering
Google LLCOfficial
Author, validate, test, and deploy YARA-L 2.0 detection rules and evaluate end-to-end detection coverage gaps in Google SecOps.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.861score
secops-hunt
Google LLCOfficial
Expert guidance for proactive threat hunting in Google SecOps.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.861score
secops-cases
Google LLCOfficial
Manage Google Security Operations (SecOps) SOAR cases throughout their lifecycle.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.861score
secops-investigate
Google LLCOfficial
Expert guidance for deep security incident and entity investigations in Google SecOps.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.824score
google-ads-api-quickstart
google-ads-api-teamOfficial
Guides developers through Google Ads API quickstart: credential setup, choosing from 6 client libraries/REST, configuring environments, and running a…
SkillBFreshness: B★ 21.5KClaude Code +9 - 0.819score
google-ads-api-mcp-setup
google-ads-api-teamOfficial
Guides developers through downloading, configuring, and installing the official open-source Google Ads MCP Server.
SkillBFreshness: B★ 21.5KClaude Code +9 - 0.815score
ima-dai-sdk
Google LLCOfficial
Integrates the Google Interactive Media Ads (IMA) Dynamic Ad Insertion (DAI) SDK into websites, web apps, mobile apps, or TV apps.
SkillBFreshness: B★ 21.5KClaude Code +9 - 0.815score
ima-sdk-client-side
Google LLCOfficial
Supports Interactive Media Ads (IMA) SDK.
SkillBFreshness: B★ 21.5KClaude Code +9 - 0.699score
gcloud
googleOfficial
Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
agent-platform-deploy
googleOfficial
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up…
SkillAFreshness: A★ 21.5KClaude Code +9
Signals
- Stars
- 21,542
- Forks
- 1,821
- Open issues
- 21
- Last commit (this folder)
- Oct 21, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.1
- License
- Apache-2.0
- Repository
- github.com/google/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from google
- 0.699score
retrieving-developer-knowledge
googleOfficial
Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and…
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
data-manager-api-setup
googleOfficial
Guides developers through client library installation and authentication setup steps for the Data Manager API.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
agent-platform-migrate-from-ai-studio
googleOfficial
Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI).
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
gcloud
googleOfficial
Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
google-cloud-recipe-onboarding
googleOfficial
Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource.
SkillAFreshness: A★ 21.5KClaude Code +9 - 0.699score
agent-platform-deploy
googleOfficial
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up…
SkillAFreshness: A★ 21.5KClaude Code +9
Cite this page
google-cloud-solution-multi-agent-security skill. Agent Mart. https://agentmart.dev/skills/google-google-cloud-solution-multi-agent-security (last updated 2026-10-24)