Model Armor

Inline screening of LLM prompts and responses for injection, unsafe content and data leaks.

Provider: gcp
Kind: Policy engine
Category: Operations
Official docs: https://cloud.google.com/security-command-center/docs/model-armor-overview

Properties · 3 set by this component

property	type	values	required	kind default	this component
effect	enum	audit \| deny \| modify \| deploy-if-not-exists	no	—	inherited
enforcementMode	enum	enforced \| disabled	no	—	inherited
enforcementType · component property	enum	inspect-only \| inspect-and-block	no	—	inherited
filterConfidence · component property	enum	low-and-above \| medium-and-above \| high	no	—	inherited
floorSettings · component property	boolean	—	no	false	inherited
loggingEnabled · component property	boolean	—	no	false	inherited
managed	boolean	—	no	false	▸ true
policyCount	integer	—	no	—	inherited
remediation	boolean	—	no	false	▸ false
scope	enum	resource \| group \| account \| organization	no	—	▸ resource

Rules that apply · 0

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

No rule reads this kind yet. That is a gap, not a guarantee.

Use it in a design

nodes:
  - { id: "model-armor", component: "google-model-armor" }

Other Policy engine products · 56

Cloud Configalibaba-cloud-configalibabacloudpolicy-engine Data Security Centeralibaba-data-security-centeralibabacloudpolicy-engine Amazon CodeGuru Revieweraws-codeguru-reviewerawspolicy-engine AWS Configaws-configawspolicy-engine AWS Control Toweraws-control-towerawspolicy-engine IAM Access Analyzeraws-iam-access-analyzerawspolicy-engine AWS Lake Formationaws-lake-formationawspolicy-engine AWS License Manageraws-license-managerawspolicy-engine AWS Organizationsaws-organizationsawspolicy-engine AWS Resource Access Manageraws-ramawspolicy-engine Amazon Verified Permissionsaws-verified-permissionsawspolicy-engine Microsoft Entra Conditional Accessazure-conditional-accessazurepolicy-engine Azure Policyazure-policyazurepolicy-engine Microsoft Entra Privileged Identity Managementazure-privileged-identity-managementazurepolicy-engine Cloudflare Data Loss Preventioncloudflare-dlpcloudflarepolicy-engine CalypsoAIcalypsoaipolicy-engine Cerboscerbospolicy-engine OPA Gatekeepergatekeeperpolicy-engine Guardrails AIguardrails-aipolicy-engine HiddenLayer AI Security Platformhiddenlayerpolicy-engine KubeArmorkubearmorpolicy-engine Kubewardenkubewardenpolicy-engine Kyvernokyvernopolicy-engine Lakera Guardlakera-guardpolicy-engine LLM Guardllm-guardpolicy-engine NeMo Guardrailsnemo-guardrailspolicy-engine Open Policy Agentopapolicy-engine Permit.iopermit-iopolicy-engine Generic policy enginepolicy-enginepolicy-engine Prompt Securityprompt-securitypolicy-engine Protect AIprotect-aipolicy-engine Rebuffrebuffpolicy-engine Robust Intelligencerobust-intelligencepolicy-engine SonarQube Serversonarqubepolicy-engine DigitalOcean CSPMdigitalocean-cspmdigitaloceanpolicy-engine Access Context Managergoogle-access-context-managergcppolicy-engine Assured Workloadsgoogle-assured-workloadsgcppolicy-engine Binary Authorizationgoogle-binary-authorizationgcppolicy-engine Identity and Access Managementgoogle-cloud-iamgcppolicy-engine Firebase App Checkgoogle-firebase-app-checkgcppolicy-engine

and 16 more → Policy engine page

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Model Armor: screens LLM prompts and responses inline against a template of filters (responsible AI,
3# prompt injection and jailbreak, Sensitive Data Protection, malicious URL). Per "Model Armor overview"
4# the service is stateless and holds nothing unless Cloud Logging is turned on, each filter carries a
5# confidence threshold, and floor settings set a project or organization baseline for all templates.
6schemaVersion: "1"
7type: "component"
8id: "google-model-armor"
9kind: "policy-engine"
10provider: "gcp"
11docs: "https://cloud.google.com/security-command-center/docs/model-armor-overview"
12defaults:
13  scope: "resource"
14  remediation: false
15  managed: true
16properties:
17  enforcementType:
18    type: "enum"
19    values: ["inspect-only", "inspect-and-block"]
20  filterConfidence:
21    type: "enum"
22    values: ["low-and-above", "medium-and-above", "high"]
23  loggingEnabled:
24    type: "boolean"
25    default: false
26  floorSettings:
27    type: "boolean"
28    default: false

The same page as markdown, for an agent: /catalogue/components/google-model-armor.md