multiAI Summary Pending
k8s-security-policies
Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.
28,273 stars
bysickn33
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/k8s-security-policies/SKILL.md --create-dirs "https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/plugins/antigravity-awesome-skills-claude/skills/k8s-security-policies/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/k8s-security-policies/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How k8s-security-policies Compares
| Feature / Agent | k8s-security-policies | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Kubernetes Security Policies
Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.
## Do not use this skill when
- The task is unrelated to kubernetes security policies
- You need a different domain or tool outside this scope
## Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
- If detailed examples are required, open `resources/implementation-playbook.md`.
## Purpose
Implement defense-in-depth security for Kubernetes clusters using network policies, pod security standards, and RBAC.
## Use this skill when
- Implement network segmentation
- Configure pod security standards
- Set up RBAC for least-privilege access
- Create security policies for compliance
- Implement admission control
- Secure multi-tenant clusters
## Pod Security Standards
### 1. Privileged (Unrestricted)
```yaml
apiVersion: v1
kind: Namespace
metadata:
name: privileged-ns
labels:
pod-security.kubernetes.io/enforce: privileged
pod-security.kubernetes.io/audit: privileged
pod-security.kubernetes.io/warn: privileged
```
### 2. Baseline (Minimally restrictive)
```yaml
apiVersion: v1
kind: Namespace
metadata:
name: baseline-ns
labels:
pod-security.kubernetes.io/enforce: baseline
pod-security.kubernetes.io/audit: baseline
pod-security.kubernetes.io/warn: baseline
```
### 3. Restricted (Most restrictive)
```yaml
apiVersion: v1
kind: Namespace
metadata:
name: restricted-ns
labels:
pod-security.kubernetes.io/enforce: restricted
pod-security.kubernetes.io/audit: restricted
pod-security.kubernetes.io/warn: restricted
```
## Network Policies
### Default Deny All
```yaml
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: default-deny-all
namespace: production
spec:
podSelector: {}
policyTypes:
- Ingress
- Egress
```
### Allow Frontend to Backend
```yaml
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: allow-frontend-to-backend
namespace: production
spec:
podSelector:
matchLabels:
app: backend
policyTypes:
- Ingress
ingress:
- from:
- podSelector:
matchLabels:
app: frontend
ports:
- protocol: TCP
port: 8080
```
### Allow DNS
```yaml
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: allow-dns
namespace: production
spec:
podSelector: {}
policyTypes:
- Egress
egress:
- to:
- namespaceSelector:
matchLabels:
name: kube-system
ports:
- protocol: UDP
port: 53
```
**Reference:** See `assets/network-policy-template.yaml`
## RBAC Configuration
### Role (Namespace-scoped)
```yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: pod-reader
namespace: production
rules:
- apiGroups: [""]
resources: ["pods"]
verbs: ["get", "watch", "list"]
```
### ClusterRole (Cluster-wide)
```yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: secret-reader
rules:
- apiGroups: [""]
resources: ["secrets"]
verbs: ["get", "watch", "list"]
```
### RoleBinding
```yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: read-pods
namespace: production
subjects:
- kind: User
name: jane
apiGroup: rbac.authorization.k8s.io
- kind: ServiceAccount
name: default
namespace: production
roleRef:
kind: Role
name: pod-reader
apiGroup: rbac.authorization.k8s.io
```
**Reference:** See `references/rbac-patterns.md`
## Pod Security Context
### Restricted Pod
```yaml
apiVersion: v1
kind: Pod
metadata:
name: secure-pod
spec:
securityContext:
runAsNonRoot: true
runAsUser: 1000
fsGroup: 1000
seccompProfile:
type: RuntimeDefault
containers:
- name: app
image: myapp:1.0
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop:
- ALL
```
## Policy Enforcement with OPA Gatekeeper
### ConstraintTemplate
```yaml
apiVersion: templates.gatekeeper.sh/v1
kind: ConstraintTemplate
metadata:
name: k8srequiredlabels
spec:
crd:
spec:
names:
kind: K8sRequiredLabels
validation:
openAPIV3Schema:
type: object
properties:
labels:
type: array
items:
type: string
targets:
- target: admission.k8s.gatekeeper.sh
rego: |
package k8srequiredlabels
violation[{"msg": msg, "details": {"missing_labels": missing}}] {
provided := {label | input.review.object.metadata.labels[label]}
required := {label | label := input.parameters.labels[_]}
missing := required - provided
count(missing) > 0
msg := sprintf("missing required labels: %v", [missing])
}
```
### Constraint
```yaml
apiVersion: constraints.gatekeeper.sh/v1beta1
kind: K8sRequiredLabels
metadata:
name: require-app-label
spec:
match:
kinds:
- apiGroups: ["apps"]
kinds: ["Deployment"]
parameters:
labels: ["app", "environment"]
```
## Service Mesh Security (Istio)
### PeerAuthentication (mTLS)
```yaml
apiVersion: security.istio.io/v1beta1
kind: PeerAuthentication
metadata:
name: default
namespace: production
spec:
mtls:
mode: STRICT
```
### AuthorizationPolicy
```yaml
apiVersion: security.istio.io/v1beta1
kind: AuthorizationPolicy
metadata:
name: allow-frontend
namespace: production
spec:
selector:
matchLabels:
app: backend
action: ALLOW
rules:
- from:
- source:
principals: ["cluster.local/ns/production/sa/frontend"]
```
## Best Practices
1. **Implement Pod Security Standards** at namespace level
2. **Use Network Policies** for network segmentation
3. **Apply least-privilege RBAC** for all service accounts
4. **Enable admission control** (OPA Gatekeeper/Kyverno)
5. **Run containers as non-root**
6. **Use read-only root filesystem**
7. **Drop all capabilities** unless needed
8. **Implement resource quotas** and limit ranges
9. **Enable audit logging** for security events
10. **Regular security scanning** of images
## Compliance Frameworks
### CIS Kubernetes Benchmark
- Use RBAC authorization
- Enable audit logging
- Use Pod Security Standards
- Configure network policies
- Implement secrets encryption at rest
- Enable node authentication
### NIST Cybersecurity Framework
- Implement defense in depth
- Use network segmentation
- Configure security monitoring
- Implement access controls
- Enable logging and monitoring
## Troubleshooting
**NetworkPolicy not working:**
```bash
# Check if CNI supports NetworkPolicy
kubectl get nodes -o wide
kubectl describe networkpolicy <name>
```
**RBAC permission denied:**
```bash
# Check effective permissions
kubectl auth can-i list pods --as system:serviceaccount:default:my-sa
kubectl auth can-i '*' '*' --as system:serviceaccount:default:my-sa
```
## Reference Files
- `assets/network-policy-template.yaml` - Network policy examples
- `assets/pod-security-template.yaml` - Pod security policies
- `references/rbac-patterns.md` - RBAC configuration patterns
## Related Skills
- `k8s-manifest-generator` - For creating secure manifests
- `gitops-workflow` - For automated policy deployment